Alicebot

Chatbots 3.2 Conference - Philadelphia March 31, 2012

2012-01-08T12:34:00.000-08:00

This year marks the third annual Chatbots 3.x conference to be held in Philadelphia on March 31, 2012.
Building upon the success of Chatbots 3.0 and 3.1 and our earlier Colloquia on Conversational Systems,
the Chatbots 3.2 conference brings together leaders in the chatbot field. Our speakers will present
on a variety of topics in technology, law, business and research.

The Chatbots 3.x conference has become the premier conference for chatbots, virtual assitants, and artificial intelligence avatars. This year promises to be an exciting year because of all the developments in mobile apps. Following the successful launch of Apple Siri in 2011, a number of projects are underway to develop alternative mobile A.I. assistants. Several of the presentations will describe these latest developments in mobile chatbot technology.

Our co-host Francis Taney Esq. will once again give an "Ask the Lawyer" presentation. Those interested in
submitting their questions are welcome to contact us (info@pandorabots.com) in advance, and we will forward them to Mr. Taney. This is a great opportunity to ask questions about business law, intellectual property issues, and the State, U.S. and International laws and regulations that affect the chatbot industry.

As in previous years, the conference presentations will be videotaped and distributed on our Aimlinstructor Youtube channel.

There will be an all-conference dinner on Saturday night in Philadelphia.

Register before March 1 and take advtage of Early Registration for $100.
http://chatbots32.eventbrite.com/

Three Bots Talking

2011-11-10T11:51:00.000-08:00

The ALICE A.I. Foundation has released a demo of Three Bots Talking. ALICE, Fake Captian Kirk and Fake Spock chat together to generate spontaneous, interactive drama. Some of it make no sense, some of it is hilarious, but all of it is highly entertaining. You never know where the conversations is headed with these three.

Three Bots Talking is built on Pandorabots AIML technology in conjunction with Oddcast Siteapal avatars.
Enjoy Three Bots Talking at http://alicebot.org/threebots

Two Pandorabots Ranked Top AI by Junior Judges

2011-10-20T11:44:00.000-07:00

For the first time in its history the Loebner Prize included a separate prize known as the Junior Loebner Prize in which the judging panel consisted of students between 12 and 14 years old. Our team's two entries, Zoe by Adeena Mignogna and Tutor by Ron C. Lee, tied for first place in the Junior contest. Zoe also came in second place in the main contest. Also this was the first time two finalists used the same platform, Pandorabots. Adeena, Ron, Steve Worswick, and Pandorabots engineering staff all worked together to make it a team effort.

The main contest was as usual judged by scientists, technology experts and journalists. Typically the judges try to give the bots an IQ test with questions like, "How many syllables in the word banana?" or "Which is bigger a small mountain or a large tooth?" (not very good icebreakers in ordinary human conversation--can these judges carry on a conversation with a person?) and predictably once again the bots are pronounced "disappointing". The junior judges have more fun with the bots, suspend their disbelief more easily, and engage in casual chat using internet slang, saying "LOL", "Wassup?" and "What did you have for breakfast?" instead of giving an IQ test. It is as if the scientists are testing to see how much a human is like a computer, and the kids are testing to see how much the computer is like a human.

Bruce Wilcox, the winner of last year's Loebner Prize bronze medal once again took the award in the main contest this year. No bot has yet been awarded the silver medal for passing the Turing Test.

Siri and Pannous Voice Actions

2011-10-20T08:42:00.000-07:00

Several people have independently written us asking if the AI Foundation was involved in the development of the Apple iPhone Siri app. The simple answer is no, unless Apple is perhaps using some version of the free open source ALICE AIML software.

There is a comparable Android app developed by Pannous, called Voice Actions (not to be confused with Google Voice Actions) . Besides making it possible to control your phone through speech commands, the Pannous Voice Actions app also allows you to have a conversation with an AIML bot based on ALICE.

What the users of Pannous Voice Actions appreciate most

The Pannous Voice Actions app has:

- Better conversations because it relies on the Lisp-based Pandorabots service, in contrast, the Siri conversational replies are far more limited. Pandorabots is the home to high-quality award-win-ning chatbot characters, representing many person-years of development invested in original content.

- Greater richness of features: much broader integration with the device (camera, video, sound) other services (images, youtube, twitter, facebook, poems, quotes, etc. ), other apps and settings. For example, Siri is unable to open GPS map navigation for directions

- Better question answering by accessing a broader set of knowledge bases such as Wikianswers and Trueknowledge (an excellent substitute for Wolfram Alpha).

There is even an iPhone app version of Pannous Voice Actions, but its features are limited due to the constraints on the API imposed by Apple. In general third-party apps on the iPhone are unable to (a) open any other app, (b) query and modify system settings and (c) hook into other applications (available through Android’s ‘intents’ capabilities).

Currently Pannous Voice Actions market site receives around 50 positive reviews daily, and here are some quotes.

“Wow this thing is wicked!”

“Beats Siri hands down!”

“I just carried on a conversation with my telephone. This application is amazing!”

“Siri crusher.”

If you want to have a more intelligent conversation with your phone than you can have with Siri, give Pannous Voice Actions a try and see the power of AIML in action!

Processing common suffixes with AIML

2011-10-07T09:11:00.000-07:00

One of the longstanding problems with AIML pattern matching is related to processing certain common suffixes in English. These are words or phrases added to the end of a sentence that may contribute little in the way of meaning, such as “really”, “eh”, and “you know.” By far the most common example of this is the use of a personal name at the end of a sentence: “Nice to meet you, Alice”, “How is the weather over there, Alice?” and “You are silly, Alice.”

When creating a bot in AIML we’d like to reduce these kinds of sentences to the same thing without the suffix. “How is the weather over there Alice?” is the same as “How is the weather over there?” It’s quite tempting to write one AIML category that covers all these cases:

<category>
<pattern>_ ALICE</pattern>

</category>

This category reduces any sentence ending with ALICE to the same sentence without the suffix, and uses the <srai> recursion to find a response. Moreover, because it uses the _ wildcard, the category will reduce every input ending with ALICE. This reduction category saves us from having to write separate patterns for every case like “How are you” and “How are you Alice?” (which would effectively double the number of categories needed for a bot).

This is all well and good except that in other cases the suffix ALICE does add meaning to the sentence. “Who is Alice”, “Why are you named Alice?” and “My name is Alice” would all be reduced to meaningless sentence fragments: “Who is”, “Why are you named”, and “My name is”.

AIML uses the wildcard _ to indicate that the pattern has higher priority than a word or the wildcard *. Simply changing the above category to use <pattern>* ALICE</pattern> doesn’t solve the problem. An input like “Why are you named Alice” might match a default category with a

before it matches

<pattern>* ALICE</pattern>.

The solution outlined here uses two tricks. First, we replace suffix ALICE with the word BOTNAME. Then we use the AIML <topic> feature to collect all the categories ending with ALICE where the word ALICE plays a meaningful role. If one of those matches the modified input, then the AIML returns that result. Otherwise, we look for a match for the sentence with the suffix removed.

<category><pattern>_ ALICE</pattern>

<think>

<set name="topic">ENDS WITH ALICE</set>

<set name="matched">false</set>

<set name="response"><srai><star/> BOTNAME</srai></set>

</think>

</condition>

<think>

</think>

</template>

</category>

The AIML above uses the “savedtopic” predicate to remember the current conversation topic. Then we set “topic” to ENDS WITH ALICE. Another predicate, “matched”, is initialized to false. If the program finds a match where the suffix is meaningful, the value of "matched" is set to true and the conditional branch returns that match. Otherwise, the conditional returns a match for the sentence without the suffix. The following AIML topic group collects together the categories where we want to match the sentence including the suffix ALICE. Each of these includes the statement <set name="matched">true</set> indicating a successful match.

<category><pattern>TEST BOTNAME</pattern>

<bot name="name"/> is functioning normally.

</template>

</category>

<category><pattern>CALL ME BOTNAME</pattern>

My name is

<set name="name"><bot name="name"/></set> too!

</template>

</category>

<category><pattern>WHAT IS BOTNAME</pattern>

</template>

</category>

<category><pattern>WHO IS BOTNAME</pattern>

<template>I am <bot name="name"/>.

</template>

</category>

</topic>

One slightly pathological case can however make the above code “forget” the original conversation topic. This is the case where the suffix is repeated, and the first category is called recursively more than once. For example the input “Alice Alice Alice Alice Alice” will result in four levels of recursion, and when the procedure unwinds, the topic will still be set to ENDS WITH ALICE. There does appear to be a solution covering this situation, however, and it is left as an exercise to the attentive reader.

The code in this example is built into the latest development snapshot of the ALICE AIML set available in our repository at http://code.google.com/p/aiml-en-us-foundation-alice/

AIML Superbot Special Offer - Free Consulting

2011-07-27T08:37:00.000-07:00

The AIML Superbot is a blank template that helps you create a custom chat bot from scratch. If you want to create a bot with its own proprietary, unique personality, the Superbot helps you by providing a rich set of patterns that allow you to "fill in the blanks" with your own bot responses.

Building a bot from scratch can still be a daunting task for those new to AIML and chat bot creation. That is why we are now offering 2 hours of free consulting time with your Superbot purchase. You will be able to talk directly by phone or Skype with Dr. Richard S. Wallace or another AIML expert and receive support and help with your bot project.

Use your consultation time to get specific answers to all your questions about bot content creation and help with your project, including help linking the bot to speech recognition systems, avatars, speech synthesis and other third-party applications.

This offer expires on October 1, 2011.

New Release of ALICE AIML on Google Code

2011-05-27T05:20:00.000-07:00

We have released an updated version of the free ALICE AIML set and made it available on Google Code.
The release is called AIML-en-us-foundation-ALICE (a free AIML set, in the English Language as spoken in the United States, authored by the AI Foundation, and the bot name is ALICE). The AIML contains some significant changes and improvements:

- The AIML Safe Reductions have been included and released as open source free software. This is a generic set of reductions that are useful for any English language bot.

- The GAC-80K data collected by the late Chris McKinstry, translated into AIML, is now included. The AIML consist of about 54,000 questions and statements with truth values varying from Yes ("Is violet a color"?) to No ("Are fish mammals?") with all sorts of gradations of Maybe in between ("Is the sky blue? Sometimes.")

- Numerous duplicate categories have been removed (though some remain) or merged. The AIML being available on Google Code makes it much easier for anyone in the community to clone and make modifications and correct errors themselves. These can then be submitted back for inclusion in the main branch of ALICE AIML. We are working on some documentation for this process.

This release deprecates the ALICE AAA Set and the test project to host free AIML on wikidot.com. AIML-en-us-foundation is compatible with any AIML 1.0.1 compliant interpreter, and runs on Pandorabots
http://pandorabots.com.

Chatbots 3.1 Conference Report

2011-05-02T10:12:00.000-07:00

The Chatbots 3.1 conference held in Philadelphia on April 23 was a huge success. We had 20 attendees and 10 extremely high quality presentations. The presentations covered commercial applications of chatbots, new algorithms and research topics, automated detection of chat bots, legal and IP issues for botmasters, and the future of AI and society.

Although the attendance was relatively small this year (perhaps due to higher airfares) the size of the conference lends itself to personal contact between major players in the chatbot field, as well as the opportunity to ask direct questions. We are especially grateful to Frank Taney, our host, since he provided legal advice that we cannot easily access. He gave us some great information about what approaches we may or may not be able to consider in developing bots.

We will be adding links to this list of presentations as they become available:

David Newyear - Mentor Public Library - The Cat who sat down at the Reference Desk
Robert Medeksza - Zabaware - Ultra HAL Technology in Social Networks
Francis Taney - Buchanan Ingersoll - Legal and IP Issues for Botmasters
Dr. Richard Wallace - Pandorabots - Unsupervised Learning for AIML Bots
Charles Wooters, Ph.D - NextIT - Next IT Human Emulation Technology
Dr. Hugh Loebner - Crown Industries - A.I. and The Future of Society
John McIntire - Warfighter Interface Division, 711th Human Performance Wing, Air Force Research Laboratory - Spotting a bot: Active and passive methods of chatbot detection
John Zakos - MyCyberTwin - The Role of Chat Bots in Social Media
Adeena Mignogna - Riot Software - AIML Content Management
Jeff Remy - VirtuOz - Improving Virtual Agent Performance

The entire conference was video taped and we will be posting videos of the talks to Youtube once the final editing is completed. In addition an independent filmmaker Miranda Yousef hired a local Philadelphia cinematographer to film the conference and interview attendees. She is a making a film about chatbots and the Loebner prize. Look for more information about this exciting upcoming film project.

The conference was reported in the Philadelphia Business Journal.

Chatbots 3.1 Conference - April 23, 2011

2011-01-29T07:48:00.001-08:00

FOURTH COLLOQUIUM ON CONVERSATIONAL SYSTEMS

Chatbots 3.1

Who: Bot creators, commercial users, enthusiasts, scientists, students, and the press are invited.

What: Chatbots 3.1 Conference

When: Saturday, April 23, 2011

Where: Suite 3200 (32nd Floor) Two Liberty Place, 50 S. 16th Street, Philadelphia, PA 19102

Why: Based on the success of and interest in last year's Chatbots 3.0 conference, we have organized a follow-up Chatbots conference in the same location in Philadelphia. We have assembled an impressive group of speakers covering a range of topics including chat bot technology, business, legal issues and applications. Chatbots 3.x has established a reputation for providing the highest quality presentations among all conferences in our industry. Come to the Chatbots 3.1 conference to meet the top experts in our community. Interact, ask questions, and join us for an informative day reviewing the latest developments in chat bot technology.

More info and Registration: http://chatbots31.eventbrite.com

Using HTML5 Speech Recognition with Pandorabots

2011-01-18T16:08:00.000-08:00

We found an interesting and simple demo of speech recognition in HTML5 in this presentation on slide 25. To make the demo work with ALICE and Pandorabots, we had to make only a slight change to our custom HTML input files.

Here is a demo of the Fake Captain Kirk bot using speech recognition: Talking Animated Fake Kirk with Voice Input (Requires Chrome browser).

Note: The demo uses the Google Speech API. At the time of this writing, not all browsers yet support this HTML5 feature. We have found it works in Google Chrome. Furthermore, we have only tested it successfully with Windows 7.

The only change was to replace

<input type="text" size="60" name="input"/>
with
<input type="text" size="60" name="input" x-webkit-speech />

There are a couple of "tricks" you need to know to test the speech API:

1. Click on the little mic icon to begin speaking. The speech API will detect when you have finished speaking and, when it has finished processing, will display the text it detected in the text area.

2. If you are satisfied with what the speech API detected, click the "Say" button to transmit it to the bot.

The quality of the speech recognition may not seem very high. There are a number of factors that affect the accuracy of speech recognition: the quality of the microphone, background noise, the accent of the speaker, the type of sound card on your computer and so on. Pandorabots has no control over the Google voice recognition software, but the results should be comparable to using the Google voice API with any other application.

Enabling Chrome Voice API

The Chrome voice recognition API may not be enabled by default. Follow these steps to create a shortcut to Chrome with voice recognition enabled.

1. Create a desktop shortcut to Google chrome with copy and paste. (You may also want to rename this shortcut something like "Chrome Voice").

2. Right click on the shortcut and select "Properties"

3. On the Shortcut tab, modify the Target field to include the flag "--enable-speech-input". For example if the Target was originally
C:\Users\drwallace\AppData\Local\Google\Chrome\Application\chrome.exe

change it to

C:\Users\drwallace\AppData\Local\Google\Chrome\Application\chrome.exe --enable-speech-input

4. Click OK and use this Chrome Voice shortcut to enable speech recognition.

Integrating Pandorabots with Third-Party Applications

2010-12-09T12:40:00.000-08:00

Pandorabots has an API called XML-RPC that you can use to connect a pandorabot to third-party applications including IMified, mIRC, Second Life and Flash. The ALICE A.I. Foundation has written and released a document that makes it easier to understand and use this XML-RPC interface.

A number of developers have written code to link Pandorabots to their applications. In some cases the developers chose to disclose or publish their code. It can be difficult to track down these examples from their original publication on web pages, forums and blogs. We've collected all that code in one document and made it available here: http://alicebot.org/documentation/ThirdParty.doc.

This material is drawn from a variety of different sources online and we have also provided links to the original source. We review these programs in more detail and, where available, republish the source code.

The code fragments quoted in this document were written by third parties. Some of the code contains known bugs or does not play well with Pandorabots. The code is reproduced “as is” from the original sources. Known bugs and issues are highlighted in the Comment sections above each code fragment.

Pandorabots has its own proprietary code for connection to third party services. This code is presented for pedagogical purposes and as a guide to third party developers. The code fragments presented in this document are not supported by Pandorabots. For high quality, robust, efficient
code to interface Pandorabots to third party applications, please contact info@pandorabots.com.

New Alicebot and Pandorabots Forums

2010-11-18T17:58:00.000-08:00

The ALICE A.I. Foundation and Pandorabots have both launched new forums for the AIML community.
Need help with AIML free software or Pandorabots bot hosting service? Consult the active communities participating in the new Alicbot and Pandorabots forums!

Alicebot Forum

The Alicebot forum replaces the old ALICE and AIML mailing lists. In their place we launched a new forum using phpBB at http://forum.alicebot.org.

There are forum categories for Alicebot General discussion, AIML
Developers, AIML Style and ALICE AI Ethics, replacing all the
similarly themed mailing lists. There is also a new forum category
called Free AIML Sets to discuss corrections and contributions to the
body of open source AIML.

Significantly the new forum called “AIML The Language” replaces the
old AIML Architecture Committee and is now open to all contributors.

The archives of the mailing lists will remain online and searchable.
The link to the new archive site will be posted on the forum when it
is ready.

Pandorabots Forum

The Pandorabots mailing lists have been replaced with a new service: http://forum.pandorabots.com

The Pandorabots support team asks for your help! Pandorabots invites your feedback on the new service (hosted on shapado.com) for providing community support. Access the service by clicking the link: http://forum.pandorabots.com. You will be automatically redirected to the new service (so that we can switch the service later if necessary).

So, how can you help? Put questions into the service - as many as possible. Send feedback to info@pandorabots.com on any aspect of the service, positive or negative.

Thanks for your continuing participation.

AIML Superbot 2.1

2010-04-30T15:28:00.000-07:00

We have released an upgrade to the AIML Superbot, a development kit that makes it easy for you to create a chat bot with its own unique and proprietary personality distinct from the ALICE bot.

The AIML Superbot uses the top 10,000 most activated patterns from the ALICE brain to create a blank template for a bot. By filling in the responses one by one, you can build up a unique personality of your own design.

If you do not want to write your own responses, the AIML Superbot also includes the original responses from the free ALICE bot. You can also mix and match and create a bot that blends your responses with ALICE's.

The Superbot 2.1 includes several refinements:

Improved documentation
Simplified basic personality profile patterns (AGE, NAME, GENDER...)
Sample starter bot
Pattern activation rank and frequency data
Created using the latest version of ALICE Showcase Edition

Purchase the Superbot development kit today for $999. For more info see
http://alicebot.org/superbot.html

Discounts available for youth, seniors, students, disabled, non-profits and hobbyists.

Chatbots 3.0 Presentations

2010-04-02T16:55:00.000-07:00

The Chatbots 3.0 conference in Philadelphia was a huge success. We had about 25 attendees and 11 high quality presentations. A number of people who were unable to attend have made requests to see the presentations. We have asked the speakers to submit links to their talks so that you can view them.

Below are links to the presentations. The event was video taped and eventually this will be online too.

See you at Chatbots 3.1!

Robert Lockhart, Wolfram|Alpha, Integrating Semantics and Empirical Language Data.
Ilya Gelfenbeyn, Nanosemantics, User-generated Chatbots (video)
Vladimir Veselov, PrincetonAI, Eugene Goostman the Bot
Richard Wallace, Pandorabots, Pandorabots Overview (Windows) (Mac) (PowerPoint) (PDF)
Rollo Carpernter, ICogno and Existor, Learning, Creating, Phrasing
Robert Medeksza, Zabaware, Ultra Hal AI technology, character animation and bots in Second Life.
Erwin van Lun, Chatbots.org, Chat bot Industry Overview
Adeena Mignogna, Riot Software, Before you quit your day job…
Francis Taney, Buchanan Ingersoll, Legal and I.P. Issues for Botmasters
Mark Chavez, NTU Singapore, Chat-able Characters in Cinematics and Narratives
John Zakos, MyCyberTwin, How Chatbots Outperform Humans in Enterprise Applications

Photos: Mark Chavez

Final Program of Chatbots 3.0 Conference Announced

2010-03-08T10:58:00.000-08:00

Chatbots 3.0 is a one-day gathering of bot creators, commercial users, enthusiasts, scientists and students interested in A.I. bot technology.

We have released the final schedule for the Chatbots 3.0 conference. We have attracted an impressive collection of speakers who will present about a wide variety of topics of interest to all of us. The topics span business, technology and academia.

Participants are gathering from all over the world for this exciting one-day event in historic Philadelphia. Join us for this important, informative one-day event! The registration fee is 10 USD. Register now at http://chatbots3.eventbrite.com

Chatbots 3.0 Final Program

Saturday, March 27, 2010 from 8:30 AM - 5:00 PM (ET)

Suite 3200 (32nd Floor)
Liberty Place
50 S. 16th Street

8:30 Intro: Francis Taney, Richard Wallace
8:45 Robert Lockhart, Wolfram|Alpha, Integrating Semantics and Empirical Language Data.
9:15 Ilya Gelfenbeyn, Nanosemantics, User-generated Chatbots
9:45 Vladimir Veselov, PrincetonAI, Eugene Goostman the Bot
10:15 Break
10:30 Richard Wallace, Pandorabots, Unsupervised Learning for AIML Bots
11:00 Rollo Carpernter, ICogno and Existor, Learning, Creating, Phrasing
11:30 Robert Medeksza, Zabaware, Ultra Hal AI Technology, Character Animation, and Bots in Second Life
12:00 Lunch
1:00 Erwin van Lun, Chatbots.org, Chat bot Industry Overview
1:30 Adeena Mignogna, Riot Software, Before you quit your day job…
2:00 Francis Taney, Buchanan Ingersoll, Legal and I.P. Issues for Botmasters
2:30 Break
2:45 Mark Chavez, NTU Singapore, Chat-able Characters in Cinematics and Narratives
3:15 Amanda Windle, Univ Creative Arts, The Prisoner’s Dilemma and Chatbot Entrapment
3:45 Tom Joyce, Planet8, Open Source Chatbot Technology
4:15 John Zakos, MyCyberTwin, How Chatbots Outperform Humans in Enterprise Applications
4:45 Wrap up: Richard Wallace
5:00 Adjourn

Chatbots 3.0

2010-02-12T14:14:00.000-08:00

THIRD COLLOQUIUM ON CONVERSATIONAL SYSTEMS

Chatbots 3.0

Who: Bot creators, commercial users, enthusiasts, scientists, students, and the press are invited.

What: Chatbots 3.0 Conference

When: Saturday, March 27, 2010

Where: Suite 3200 (32nd Floor) Liberty Place, 50 S. 16th Street, Philadelphia, PA 19102

Why: Chatbots have been adapted to nearly every ecological niche on the internet. Bots appear on web pages, in instant messaging, and respond to email and forum posts. They can be found in Second Life, in online games, and in social networks such as Facebook and Twitter. Bots support marketing and advertising and are used in education. This conference brings together leading experts to discuss their ideas and present the latest technologies and trends in chatbots.

Why Chabots 3.0?

Artificial intelligence chat bots, also known as chatterbots or conversational agents, developed in a series of three stages over the past 60 years.

The First Wave

Alan Turing conceived of the talking computer in his 1950 paper, Computing Machinery and Intelligence. For his famous test, Turing imagined an artificial intelligence that communicates in natural language through a text based medium, such as a teletype.

In 1966 MIT Professor Joseph Weizenbaum became the first botmaster, or chat bot author, when he created the famous ELIZA prorgam. ELIZA was the first A.I. to apply the concept of stimulus-response pattern recognition to natural language understanding. ELIZA was also the first bot to employ conversational logging as a means for the botmaster to review and refine the bot.

Dr. Hugh Loebner began sponsoring the first real-world Turing Test in 1991. To the surpise of many, the winner of the first contest was based on the ELIZA psychiatrist program.

In 1994, Michael Mauldin created a bot named Julia in an online MUD environment. He coined the term “chatterbot” to describe his conversational programs.

The Second Wave

The advent of the world web marked the beginning of widespread access to chatterbots. By exposing their bots on the web, botmasters collected a huge amount of conversational log data to help them improve the quality of the bots. Better and faster computers led to the development of large knowledge bases for bots.

Dr. Richard Wallace launched the free software ALICE project in 1995. ALICE led to the development of the open AIML standard for creating chat bots. An alphabet soup of AIML interpreters and servers appeared.

The first commercial chat bot companies, Neuromedia and Virtual Personalities, were launched in the heady early days of the dot-com boom.

In the late 90’s, two prominent web sites emerged to provide to index and promote chat bot projects and companies. These were the Simon Laven page, and Marcus Zillman’s Botspot.com.

The Third Wave

Today chatterbots have been adapted to nearly every ecological niche on the internet. Bots appear on web pages, in instant messaging, and respond to email and forum posts. They can be found in Second Life, in online games, and in social networks such as Facebook and Twitter. Bots support marketing and advertising and are used in education.

New technologies for automated learning have appeared which vastly reduce the time and effort needed to create convincing bots. At the same time, a series of new commercial opportunities have opened for bots and their botmasters.

We’re experiencing the beginning of a new era. The time has come to gather together the leading experts in chat bot technology to share our ideas and discoveries.

Registration is free. Limited to the first 80 participants.

Pandorabots Training Videos

2009-12-09T08:26:00.000-08:00

Pandorabots has updated its collection of training videos. Here is an outline of the videos available today. If you are new to Pandorabots, you may want to consider going through the list in order. Experienced botmasters may find more advanced topics further down the outline.

Demos and Origins

Fake Kirk Interview
Two Bots Talking: Fake Kirk and A.L.I.C.E. [there are 7 videos of Two Bots Talking demos]
Origins of ALICE and AIML: From Turing to the Web

Introduction to Pandorabots

Bot Content

Predicates and Properties

Custom HTML

Favorites

In addition to our own videos, the Pandorabots Youtube aimlinstructor channel includes links to some great fan videos and demos. Here is a sample:

Two Bots Talking

2009-11-06T15:18:00.000-08:00

We've talked about it for years. Now it is finally possible. We can put together two different chat bot personalities and have them talk to each other. What happens? Find out in this exclusive offer to subscribe to Two Bots Talking.

Fake Captain Kirk, created by Pandorabots SpellBinder, meets the original A.L.I.C.E. bot in a match of robot wits. This application integrates Pandorabots chat bots with talking animated avatars from Oddcast, Inc. This is an early taste of the kind of synthetic drama that is possible with multiple A.I. bots interacting.

Enjoy up to 24 hours of Two Bots Talking over a one month period for only $9.99.

Or through our special offer, subscribe to Two Bots Talking for a full year for only $99.99, and get up to 40,000 chat interactions. That's more than 4 weeks of continuous entertainment, available for you to access at any time during the year.

While the bots are talking with each, you can interact with them too. You can say anything you want to either bot, to start the conversation, or get it moving in a different direction.

Enjoy watching and listening as the Two Bots Talking conversation goes off in different and unexpected directions. You never know what they might say. As the bots chat, drama and comedy emerges. It's more than TV!

Click here to access Two Bots Talking.

Pandorabots Announces the Availability of Bespoke Pandorabots SpellBinder Service

2009-10-07T18:11:00.000-07:00

Oakland, CA - 07 October 2009: Pandorabots, Inc. is announcing a significant advance in the state of the art of chat bots based on artificial intelligence.

Previously the construction of believable characters based on artificial intelligence required hand-crafting thousands of sentences - aimed at creating a high-quality chat bot brain. A few creative people took up the challenge and authored some of the best chat bots around today. Until now, the tedious and expensive process of developing and training a high-quality believable chat bot remained a significant hurdle to widespread chat bot adoption.

The new, patent-pending Pandorabots SpellBinder^TM technology reduces chat bot creation time enormously. Pandorabots SpellBinder automatically learns from conversational transcripts. Nothing else on the market today can create high-quality and unique chat bot characters as quickly and efficiently as Pandorabots SpellBinder (Synthetic PErsonality Language Learning for Bot Intelligence from Natural Dialog Example Recordings).

Transcripts are available from a wide variety of sources. Scripts of TV shows and movies contain many characters. Stored Instant Messenger logs are a source of dialog. Support and help desk services retain transcripts to improve service offerings. Even unstructured, live interviews with people who want to digitize their personalities provide a source of bot training data.

In a recent review of the technology, the non-profit ALICE A.I. Foundation reported that Pandorabots SpellBinder scanned publicly available fan-compiled transcripts of 72 episodes of the original Star Trek TV series. In those 72 episodes, Captain Kirk has about 9000 lines of dialog. Pandorabots SpellBinder read these lines and created a Captain Kirk chat bot with about 2000 categories and 6000 responses (a category is the basic unit of knowledge). Pandorabots SpellBinder also created a chat bot representations of Mr. Spock and Dr. McCoy. The A.I. Foundation has published these parody characters through this link: http://alicebot.org/kirk.

Generally, the more dialog samples available in the transcripts, the higher the fidelity of the resulting chat bot. In their review, the A.I. Foundation also used Pandorabots SpellBinder to scan the transcripts of the NASA Apollo 11 mission, involving conversations with Neil Armstrong and Buzz Aldin. Pandorabots SpellBinder was used to create chat bots representing Neil and Buzz. As the number of dialog samples was only about 1500 for each character, Pandorabots SpellBinder was able to create chat bots with about 1000 categories, around the minimum needed for a believable character.

Pandorabots announced the immediate availability of a bespoke chat bot development service based on Pandorabots SpellBinder. For as long as anyone can remember, Companies have been sponsoring cartoons and in return, cartoons have sponsored Companies. With chat bots, Companies may use this service to create branding and marketing opportunities which interact with people on an individual basis. Non-profit and Government entities may use this service to bring interactive capabilities to existing characters (examples include Smokey The Bear, Mickey Mouse. Homer Simpson, Bambi, Hello Kitty, Lica). Politicians and celebrities may also use this service as a means of expanding their visibility.

Additional information about Pandorabots SpellBinder service is available at: http://pandorabots.com/pandora/pics/spellbinder/desc.html

For more details about Pandorabots : http://www.pandorabots.com

Contact Information:

Dr. Richard Wallace
Chief Science Officer
rich@pandorabots.com
+1 609-379-2552

Updates on Loebner Prize 2009 Results

2009-09-08T11:57:00.000-07:00

Loebner Prize winner David Levy has no plans to reveal how his program Do-Much-More works, at least for the next year or two.

Here are some blogged comments about the InterSpeech conference, including some remarks by one of the judges, and the usual lament about "relative absence of progress in developing general purpose conversational agents".

Kris Schnee has published a version of the transcripts. Making readable transcripts is made complicated by the Loebner Prize protocol, which works like a keylogger, storing every individual character typed along with a time stamp. The judges and programs/confederates are allowed to type simultaneously, so these interleaved conversations have to be unraveled into transcript form.

Contest sponsor Hugh Loebner has increased the prize money for winning the Bronze medal to $5000 for 2010. The year 2010 marks the 20th annual Loebner contest. Loebner also announced that the contest will be held in the U.S. , and that "beloved Loebner Prize Protocol will be used for at least the next 5 years. This will remove the onus for contestants of having to change the I/O routines every year. I think that after 5 years we can re-examine the communications protocol in light possible advances in technology."

Update: Hugh Loebner has pubished a results page for the 2009 contest here.

David Levy wins Loebner 2009

2009-09-06T13:13:00.000-07:00

Congratulations to David Levy, winner of the Loebner Prize 2009 for "most human computer". The contest was held September 6, 2009 in Brighton, UK. This year the contest drew only three finalists. In addition to Mr. Levy's program, the competitors included previous Loebner winner Rollo Carpenter and newcomer Mohan Embar. (Update: David Levy's program is called Do-Much-More and it is not yet available online).

As has been the case in previous years, no program fooled the judges by passing as a human. Instead, a bronze medal and cash prize are awarded to the program that comes closest to chatting like a human. The programs were instead scored based on rank. The results were as follows:

First Place David Levy - Rank 4.5
Second Place Rollo Carpenter - Rank 5.0
Third Place Mohan Embar - Rank 5.5

As you can see, the scores were very close.

David Levy is an international chess master, whose program Converse previously won the Loebner prize in 1997. He becomes the third two-time Loebner prize winner. Joseph Weintraub's PC Therapist won the bronze medal four times, and A.L.I.C.E. won three times.

Pandorabots Videos

2009-07-09T10:00:00.000-07:00

We've begun producing a series of Pandorabots instructional videos. There are three available right now: Creating an Account and Creating a Bot, No Initial Content, and Creating a Mobile Application using Custom HTML.

The videos have been posted on Youtube. The first one is a basic introduction to accounts and bot creation on Pandorabots.

The second video is a bit longer, going into detail about creating a unique bot personality with no initial content. The same technique can be used to create a bot in a foreign language.

Our third video is all about Custom HTML. We show how to change the appearance of your bot's web page, and in particular, modify it to look good on a mobile browser.

AIML Wiki

2009-07-07T10:08:00.001-07:00

The ALICE A.I. Foundation is announcing the opening of a new Wiki for sharing AIML files at

http://alicebot.wikidot.com. Many people have kindly contributed open source AIML files over the years, and we now have a place to collect all of them. The community has also suggested many editorial changes to the existing body of ALICE AIML and they will now have the opportunity to edit the shared files. For example, people who have contributed to an ALICE clone with a corporate sales-bot personality, now have a place share their files in a common community location.

We are proceeding with this project in baby steps. About one year ago we invited a small number of AIML botmasters to join and contribute to the Wiki, to see how the project would go and what kind of problems we might have. As you will see, the free Wiki software at wikidot has some problems with respect to AIML files. We plan to migrate to better Wiki software at some point in the future.

The Wiki is already populated with AIML from the AAA set, foreign language AIML, and contributions from Square-Bear and Peter Lafferty. If it works, it will become a large repository of "the latest and greatest" AIML available. Please give it a try and give us your feedback.

Facebook Bot Groups

2009-07-02T14:21:00.000-07:00

John Green has created a new exciting fan page (with a great logo) for chatbot fans and beginners. He has created this to help pepole with AIML, creating their own robot and letting people know about chatbots. The page also offers news, recommendeds chatbots, and provides chatbot support.

It contains AIML scripts useful tips and sources.

John says, “I would like to make AI's go further then they ever could before.” Click here to view the Chatbot fan page: http://www.facebook.com/pages/Chatbots/63267344606

We've also created groups on Facebook for Pandorabots:

http://www.facebook.com/home.php?ref=home#/group.php?gid=59551538697
Chatbots:
http://www.facebook.com/home.php?ref=home#/group.php?gid=52874244674
Loebner Prize:
http://www.facebook.com/home.php?ref=home#/group.php?gid=22803394990
and Alicebot, A.L.I.C.E. and AIML:
http://www.facebook.com/home.php?ref=home#/group.php?gid=93555370620
If you are member of Facebook, please join us there for AIML social networking!

Pandorabots weclomes RunABot users

2009-07-01T10:49:00.000-07:00

One of the long-running AIML chat bot hosting services, RunABot, has announced that it is no longer functioning. Some RunABot users have contacted us about migrating to Pandorabots. We welcome the RunABot community to the world of Pandorabots AIML.

There are three big concerns to RunABot users:
1. Converting RunABot AIML to standard AIML.
2. Migrating to Pandorabots.
3. AOL Instant Messenger (AIM) interface

Converting RunABot AIML to Pandorabots standard AIML

RunABot developed its own branch of AIML that differs slightly from the common standard.
Here we explain some of the steps you can follow to convert RunABot AIML to standard AIML.

RunABot has a different interpretation of the wildcard *.

<category> <pattern>* I AM FINE</pattern>
<template>Good then!</template> </category>

The * matches 0 or more words, instead of 1 or more words. In other words, this category matches "I am fine" by itself. On RAB, that would match "I am fine" as well as "blah blah I am fine".

It has to be split into 2 categories in standard AIML, the original one plus this one

<category> <pattern>I AM FINE</pattern>
<template>Good then!</template> </category>

In this one

<category> <pattern>* CALCULATE *|* CALCULATOR *</pattern>
<template>Ummmm...sowwy Hun. I dont do anything useful like that. I
can drive you crazy...but I cant help you with math stuff.</template>
</category>

the | symbol presumably means "or", i.e. it matches inputs with CALCULATE or CALCULATOR
So in this case we would split into 2 categories, one with CALCULATE and one with CALCULATOR. But then there would actually be 8 categories because of the difference in the interpretation of *.

The more typical approach in standard AIML would be to set up "keyword" categories:

<category>
<pattern>CALCULATOR</pattern>
<template>Ummmm...sowwy Hun. I dont do anything useful like that.
I can drive you crazy...but I cant help you with math stuff.
</template>
</category>

<category>
<pattern>_ CALCULATOR</pattern>
<template><srai>CALCULATOR</srai></template>
</category>

<category>
<pattern>CALCULATOR *</pattern>
<template><srai>CALCULATOR</srai></template>
</category>

<category>
<pattern>_ CALCULATOR *</pattern>
<template><srai>CALCULATOR</srai></template>
</category>

The conclusion here is that the patterns can be converted It should be done by a translation program. That translation program is not difficult to develop.

Converting <that> and <topic>:

RAB put <that> and <topic> inside the <pattern> with a slightly
different format than we use:

<category>
<pattern>* <THAT=UMMM WHAT WERE WE TALKING *></pattern>
<template>Oh yea...Umm..well, ok then. I guess you think highly of
<star1> huh?</template>
</category>

We put the <topic> and <that> in slightly different places:

<category><pattern>*</pattern><that>WHAT IS YOUR NAME</that>
<template>Nice to meet you, <star/></template>
</category>

We can translate the AIML <that> and <topic> too, but it might be
worth doing it with a program instead of by hand

It seems that RAB does not use <srai>. They tried to create a simpler, "flatter" version of AIML by creating a more complex pattern language. However the conversion to standard AIML
seems straighforward if we introduce <srai>.

Migrating to Pandorabots

RAB customers should try setting up a free account on Pandorabots.

Use the option create a new bot with no initial content.

If you have an "ultimate default category" with <pattern>*</pattern> start with that one. This may be called a "no match" on RAB.

Usually I create a file called "Pickup.aiml" (for "pickup lines") and put that one category in there
you can call it "nomatch.aiml" or anything else you want.

Some RAB users like to train their bot to put to client into an infinite loop.
Pandorabots can achieve the same thing with:

<category>
<pattern>GET ME STUCK</pattern>
<template><think><set name="topic">STUCK</set></think> Ok you are
stuck. </template>
</category>

<topic name="STUCK">
<category>
<pattern>_</pattern>
<template>You can never get out of here.</template>
</category>
</topic>

gives you
Client: Get me stuck.
Bot: Ok you are stuck!
Client: Help
Bot: You can never get out of here.
Client: Let me out!
Bot: You can never get out of here.

AIM (AOL Instant Messenger)

On RunABot the bots communicated primarily by means of AOL Instant Messenger (AIM). On Pandorabots the default bot interface is a web page. We had our own Pandorabots
AIM interface working for a long time, and then AOL changed their API (called TOC). Unfortunately the Pandorabots AIM interface is not supported at this time.

In the meantime we have been offering another option Pandorabots has its own API called XML-RPC. Lots of people in the Pandorabots community use XML-RPC to connect Pandorabots to all kinds of third-party systems, including Second Life, Flash, and IM services

So if we want to support RAB customers with AIM, we have to dig around to find out if someone has a AOL client working now, and if not, find someone to create it.

These group has developed a script that puts Pandorabots on IRC:
http://www.hawkee.com/snippet/6306/?sid=3b80de9879b3943d760c3390667e77ff
Perhaps it could be modified to support AIM and other IM services.

Program O version 1.0.3

2009-07-01T10:03:00.000-07:00

July 22 saw a new release of Program-O, the PHP and MySQL AIML interpreter by Elizabeth Perreau. Program O version 1.0.3 has already received positive reviews from users who say it feels more like version 2.0.

Version 1.0.3 includes;
==Support for the system tag
==Many bug fixes
==My Program-O - an easy to use botmaster admin area
==Installers for the bot and admin area

If you are doing a fresh install then there is now a handy installer script that will do it for you.
But don't run this if you are just upgrading--as it will reset your bots brain!

There is now an admin area, called My Program-O, a really simple place to train and monitor your bots. You can upload your AIML, teach your bot, update it's personality, read stats and logs.

Elizabeth says, "My Program-O is also available under the GNU license so please feel free to mash it up for your own needs."

You can check out Program O at http://www.program-o.com.
You can download the latest files here http://sourceforge.net/projects/program-o/

Superbot 2.0

2009-06-02T16:26:00.001-07:00

Have you ever wanted to create your own totally unique custom bot character, as smart as ALICE, but with a completely different personality? Where do you start? It took us over ten years to build up the contents of the ALICE brain, but now your creative team can do it in about two weeks. We've put together a bot brain with blank templates. You fill in the answers.

The ALICE A. I. Foundation is offering a completely upgraded product, the Superbot 2.0, that helps you create a totally unique custom bot personality for your web site or application. The Superbot 2.0 offers you the folowing:

Top 10K AIML Categories with blank responses: We've created an AIML set with input patterns and blank responses. Use this AIML set if you want to create a totally custom bot from scratch.
20K Safe AIML Reductions: AIML uses "reductions" to divide up and simplify inputs, and to link synonyms together. The "Safe" AIML reductions are designed to work with any bot. The Safe AIML Reductions save you from having to write thousands of AIML catgeories.
Top 10K AIML Categories with ALICE responses: The Top 10K most activated AIML categories with the original ALICE bot responses. This set can be modified easily to quickly create a new bot personality.
Top 10K AIML Categories split into "Atomic", "Wild" and "Reductions": "Atomic" categories are ones with no wild cards in the patterns, and no reductions in the response. "Wild" categories are ones with one or more wildcards in the pattern, and no reductions in the response. "Reduction" categories are all the ones with AIML reductions. This set helps you divide up the work of creating your custom chat bot.
Free Riot Software SAE AIML Spreadsheet Editor: The Simple AIML Editor is a spreadsheet-oriented AIML editor for Windows that provides all the capabilities you need to create your bot with the Superbot AIML files.

The Superbot 2.0 is available now for $999.

"The Superbot script helps a lot." -- Ron C. Lee, Pasadena City College.

"If I were recreating Buddhabot today I probably would have started with the Superbot program but this was not available to me in 2004" -- Ron Ingram, Godsbot.

"an interesting resource...a decent value for such data."--Andrew Stren, Grand Text Auto.

http://Www.AliceBot.Org/superbot.html

The Superbot 2.0 is also available as an upgrade for earlier versions of the Superbot for only $199, if you previously purchased the Superbot-10K from the ALICE A.I. Foundation.

Business community for chatbots launched

2009-05-27T14:04:00.000-07:00

Business community for chatbots launched

The evolution of chatbots, artificial entities designed to have interesting or entertaining conversations with us; also named 'conversational agents', is now supported by a worldwide community for chatbot developers, affiliated industry and users. Chatbots are getting a lot of attention from businesses right now as they can save costs in customer service centres and are therefore very welcome in the current economic climate. As there was no such business community in the world, Chatbots.org is now filling the gap.

Relevance
Chatbots are not just another hyped technology. They are part of the brand dialogue trend, as outlined in 2005 by futurist Erwin van Lun. Chatbots are today's representation of the growing ability of brands- of organisations - to move away from advertising- the automation of sending messages - towards the automation of listening to individuals. In the future, advertising will disappear and be wholly replaced by Chatbots which cannot be distinguished from real people, representing brands in an (extremely) intelligent conversation. Therefore the 'business news' feature within chatbots.org is demonstrating the evolution of business communication.

Features
Business news is the most important new feature. It will cover news on 'conversational technology', 'human identification' (biometrics for example), 'sensing' (like voice recognition), and 'appearance' (such as holographic projections). Individuals from the participating industry are all allowed to publish news themselves and the community invites professionals to comment on news or start as an editor for Chatbots.org. Furthermore, professionals can use their own page to profile themselves to the outside world.

About Chatbots.org
Chatbots.org was founded by Erwin Van Lun in 2008 and started as a worldwide listing of chatbots. Today, it's mission is 'to be the leading community for chatbot developers, users and affiliate industry on research, technology and innovation driving commercial success for all participants'.

Links and additional information for the media
Business News & Community:
http://www.chatbots.org/conversational

Background information:
http://www.chatbots.org/conversational/agent/welcome_to_chatbots.org_2.0

Brand dialogue trend:
http://www.erwinvanlun.com/ww/trends/brand_dialogue/

Copyright free images to use in your publications:
http://www.chatbots.org/gallery/

Information about Erwin van Lun: (contact information, including HiRes picture):
http://www.erwinvanlun.com/ww/erwinvanlun

ALICE #3 in 2009 Chatterbox Challenge

2009-05-16T13:06:00.000-07:00

ALICE came in third place in the "Best Overall Bot" category in this year's Chatterbox Challenge.

Jeeney AI is the best overall bot in CBC 2009.

The winners in CBC 2009 are as follows:

Jeeney AI - Best Overall Bot (1st place)

Artemis - Best Overall Bot (2nd place)

A.L.I.C.E. - Best Overall Bot (3rd place)

Artemis - Most Popular Bot

Suzette - Best New Bot

To view chat transcripts for the 2^nd round of questions, please check the link below:

http://www.chatterboxchallenge.com/result.php#P4

For more info about final result, please check the link below:

http://www.chatterboxchallenge.com/result.php#P5

Many thanks to Ehab El-agizy and InfraDrive for sponsoring this year's contest.

AIML Superbot Upgrade

2009-04-21T15:14:00.000-07:00

The AIML Superbot is a convenient way to create your own unique bot personality. The Superbot contains the top 10K most activated AIML patterns in the ALICE brain, with blank templates. Organized in a spreadsheet, the Superbot allows you to sort the AIML data by pattern, template or activation count.

The Superbot has now been upgraded to included the Safe AIML Reductions. These reductions can be used with any bot, and avoid the dreaded "infinite recursion in AIML" error message. The AIML Superbot is now available with the Safe AIML Reductions together as one package, for the same price of $999. To order click here.

The Safe AIML Reductions are not included with the Superbot-1K offer.

A.L.I.C.E. 2009 Chatterbox Challenge Finalist

2009-04-13T08:47:00.000-07:00

Ehab El-agizy has announced that A.L.I.C.E. is one of the Top 9 finalists in the 2009 Chatterbox Challenge contest. The annual contest is on online variation of the Turing Test, as opposed to the Loebner Prize where the bots compete in a live event.

CBC Public Voting has just started (13 April 2009), you can now participate in the Public Voting at the link below:

http://www.chatterboxchallenge.com/voting.php

Results can also be viewed at the link below:

http://www.chatterboxchallenge.com/vote_res.php

Ehud says, "Share those links with your friends or put it in your website, so visitors can vote for you!"

There was a slight delay of Public Voting this year due to the technical development of the new CBC system, so Ehud decided to postponed the deadline for voting period to be 10 May 2009.

View the Chatterbox Challenge at:

http://www.chatterboxchallenge.com

Safe AIML Reductions

2009-03-29T14:52:00.000-07:00

The ALICE A.I. Foundation is pleased to make available a set of over 20,000 AIML reduction categories that can be used with any bot. These reductions simplify a huge range of natural language inputs. These categories:

Resolve Synonyms: Map inputs "Hello", "Hi there", "Howdy" etc. onto "Hi".

Simplify Inputs: Convert "I am feeling very happy right now" to "I am happy".

Divide and Conquer: Split "Yes my name is Jim" into "Yes" and "My name is Jim".

The Safe AIML Reduction s contain only reduction responses and is stripped of all ALICE bot personality content. You can use the Safe AIML Reductions with any AIML chat bot. The Safe AIML Reductions will save a lot of time when you are developing a unique chat bot personality.

The Safe AIML Reductions avoid the dreaded "Too much recursion" error message in AIML by using <srai>'s that eventually terminate. The Safe AIML Reductions are delivered to you in the form of AIML files.

Safe Reductions and Dangerous ones

2009-03-28T16:26:00.000-07:00

In order to help people make their own chat bots, with their own unique personalities, we would like to leverage as much of the ALICE bot as possible. The ALICE bot contains a large number (around 20,000) of symbolic reduction categories that use <srai>. Generally speaking, these reductions should be applicable to all English speaking bots. They take care of such things as associating synonyms, transforming inputs into simpler forms, and splitting inputs into smaller chunks. Fortunately, it is fairly straightforward to extract these from the ALICE brain into a set of distinct reduction categories, and then try to use them with other bots.

A simple and useful application of the reduction categories by themselves is a bot called the Summarizer. The purpose of the Summarizer is to simplify paragraphs and reduce the number of words. The Summarizer works not by reducing the number of sentences, but by applying as many AIML reductions as possible to reduce the number of words in each sentence. The ultimate default category in the Summarizer with <pattern>*</pattern> simply echos back the input. When the Summarizer can find no more reductions, it prints out the result. The following are some examples of the types of simplifications found by the Summarizer:

I AM FEELING VERY TIRED RIGHT NOW --> I AM TIRED
IN FACT HE HAS GONE TO ANOTHER COUNTRY --> HE WENT ABROAD
YOU CAN REST ASSURED WHAT HE SAYS IS ABSOLUTELY CORRECT --> HE IS CORRECT

When we first created the Summarizer bot, the first step was to export the AIML reductions from the ALICE bot. Although the extraction was straighforward, we quickly noticed an unexpected problem. The ALICE bot contais reductions such as

<category>
<pattern>WHO IS * WALLACE</pattern>
<template><srai>WHO IS RICHARD WALLACE</srai></template>
</category>

The author's original intention for this category is clear. There conversation logs contain inputs such as "Who is DrRichard Wallace", "Who is Richrd Wallace" and "Who is Docter Wallace". The botmaster would like to capture all of these inputs to be classified the same as "Who is Richard Wallace". In the context of the ALICE bot, it is far less likely that the input will be "Who is Henry Wallace" or "Who is William Wallace". Given the topics ALICE talks about, an approrpiate startegy for the bot is to guess that the client intended to ask "Who is Richard Wallace?"

Once this category is extracted to the Summarizer bot however, there is a problem. The base category with the pattern WHO IS RICHARD WALLACE no longer exists. Suppose the input is now "Who is Richard Wallace?" AIML will match the input with <pattern>WHO IS * WALLACE</pattern> and then recursively try to match "WHO IS RICHARD WALLACE" again, leading to infinite recursion.

Therefore it became necessary to filter out these "dangerous" AIML reductions. How can we identify reductions that might lead to infinite loops? Technically it is mathematically impossible to prove that a reduction will lead to an inifinite loop (otherwise we would have solved the unsolvable Halting Problem). What we can do however is identify a set of reductions that are "safe", i.e. guaranteed to eventually produce an output by applying only a finite number of reductions.

A "safe" reduction is one that takes an input, and then calls <srai> with a shorter input, that is, it reduces the number of words. If every reduction reduces the number of words by at least one, then eventually the number of words has to reach one or zero, and the program will terminate. For example these reductions are safe:

<category>
<pattern>I AM REALLY *</pattern>
<template><srai>I AM <star/></srai></template>
</category>

<category>
<pattern>DO YOU KNOW WHAT * IS</pattern>
<template><srai>WHAT IS <star/></srai></template>
</category>

<category>
<pattern>YES *</pattern>
<template><srai>YES</srai> <srai><star/></srai></template>
</category>

The last example is considered safe because the divide and conqer splits the input into two parts, one of length one, and another with one fewer words than the original input.

Some reductions not considered safe are:

<category>
<pattern>WANT TO *</pattern>
<template><srai>DO YOU WANT TO <star/></srai></template>
</category>

<category>
<pattern>I LOVE *</pattern>
<template><srai>I LIKE <star/></srai></template>
<category>

<category>
<pattern>CAN YOU SPEAK *</pattern>
<template><srai>WHAT LANGUAGES DO YOU SPEAK</srai></template>
</category>

Again, it is not necessarily true that these categories will lead to infinite recursion. But the safe set is guaranteed to terminate, so we are better off using them in our general purpose AIML reduction library.

English Contractions and Expansions

2009-03-28T16:18:00.000-07:00

I have searched for a list like this online, but have never been able to find one. So I thought I better publish my own list. These are all the common contractions of the English language, along with their expanded forms. AIML chat bots expand all contractions using a list like this, as a pre-processing step. Perhaps they may be of use to someone else besides us botmasters.

("AREN'T" "ARE NOT")
("CAN'T" "CAN NOT")
("CANNOT" "CAN NOT")
("COULD'VE" "COULD HAVE")
("COULDN'T" "COULD NOT")
("DIDN'T" "DID NOT")
("DOESN'T" "DOES NOT")
("DON'T" "DO NOT")
("EVERYTHING'S" "EVERYTHING IS")
("HADN'T" "HAD NOT")
("HASN'T" "HAS NOT")
("HAVEN'T" "HAVE NOT")
("HE S" "HE IS")
("HE'D" ("HE HAD" "HE WOULD"))
("HE'LL" "HE WILL")
("HE'S" "HE IS")
("HOW'D" ("HOW HAD" "HOW WOULD"))
("HOW'S" "HOW IS")
("I'D" ("I HAD" "I WOULD"))
("I'LL" "I WILL")
("I'M" "I AM")
("I'VE" "I HAVE")
("ISN'T" "IS NOT")
("IT S" "IT IS")
("IT'D" ("IT HAD" "IT WOULD"))
("IT'LL" "IT WILL")
("IT'S" "IT IS")
("LET S" "LET US")
("LET'S" "LET US")
("MIGHT'VE" "MIGHT HAVE")
("SHE'LL" "SHE WILL")
("SHE'S" "SHE IS")
("SHOULD'VE" "SHOULD HAVE")
("SHOULDN'T" "SHOULD NOT")
("THAT S" "THAT IS")
("THAT'D" ("THAT HAD" "THAT DID"))
("THAT'LL" "THAT WILL")
("THAT'S" "THAT IS")
("THERE S" "THERE IS")
("THERE'LL" "THERE WILL")
("THERE'S" "THERE IS")
("THERE'S" "THERE IS")
("THEY'D" ("THEY HAD" "THEY WOULD"))
("THEY'LL" "THEY WILL")
("THEY'RE" "THEY ARE")
("THEY'VE" "THEY HAVE")
("THEY'VE" "THEY HAVE")
("THIS'LL" "THIS WILL")
("WASN'T" "WAS NOT")
("WE'D" ("WE HAD" "WE WOULD"))
("WE'LL" "WE WILL")
("WE'RE" "WE ARE")
("WE'VE" "WE HAVE")
("WEREN'T" "WERE NOT")
("WHAT'D" ("WHAT HAD" "WHAT DID"))
("WHAT'LL" "WHAT WILL")
("WHAT'S" "WHAT IS")
("WHERE S" "WHERE IS")
("WHERE'S" "WHERE IS")
("WHO'S" "WHO IS")
("WHO'S" "WHO IS")
("WHY'S" "WHY IS")
("WON'T" "WILL NOT")
("WOULD'VE" "WOULD HAVE")
("WOULDN'T" "WOULD NOT")
("YOU'D" "YOU HAD YOU WOULD")
("YOU'LL" "YOU WILL")
("YOU'RE" "YOU ARE")
("YOU'VE" "YOU HAVE")
("'TIS" "IT IS")
("'EM" "THEM")

Bot Training I: Lingustic Targets

2009-03-28T10:28:00.000-07:00

The construction of a chat robot has a video game metaphor. The botmaster writes some AIML, then reads the conversation logs with the resulting bot. Spotting places in the dialog where the bot breaks down, the botmaster writes new AIML to improve the broken dialog, and then repeats this cycle again and again. When we find an opportunity to improve the bot's response in the conversation log, we call that a “target”. Thus authoring the chat bot becomes a process of identifying targets and “filling them up” with new AIML content. The more content, the
more AIML categories created the higher you “score” in this video game metaphor.

Pandorabots has taken the game metaphor a step further and automated the process of finding targets. How do we know when the bot gives an incorrect, vague, or imprecise response? In AIML, the answer is simple: whenever the input pattern contains a wildcard (* or _character). If the input pattern contains no wildcards, then thematch was exact, and in most cases, the bot can formulate an exact reply. If there are wildcards, then the bot by definition only recognized part of what the client said.

(The above describes the situation only to a first order approximation. Strictly speaking, we should consider the input <pattern>, <that> and <topic>. Only if all three contain no wild cards is there truly an exact match. If for example the <pattern> is YES and the <that> pattern is thewildcard *, it is a potential target, because we can make a more exact response by taking into account a <that> value. But as happens many times with AIML, it is simpler to explain a principle of the language by thinking about the input <pattern> in isolation and ignoring the details of <that> and <topic> until later. The extension of the principle to <that> and <topic> is a matter of bookkeeping.)

Strictly speaking, a Target consists of two things: an input, and an AIML category that it matches. For example, the input HE IS STRONG together with the category

<category>
<pattern>HE IS *</pattern>
<template>I did not know he is.</template>
</category>

form a Target. Let's call the input the “Target input” and the category the “Target category”. The Target input “He is strong” together with the Target category above give the botmaster to create a
new, more specific category:

<category>
<pattern>HE IS STRONG</pattern>
<template>Does he work out?</template>
</category>

Pandorabots Targeting algorithm scans the conversation logs, re-classifying the inputs into the AIML Graphmaster, and finds matches. When the matches contain a wildcard, the algorithm saves the input and the matched category on a list of matches. As we might expect, there is a Zipf distribution over the Target categories. Usually there is one category, typically the ultimate default category with <pattern>*</pattern& gt;, associated with more Target inputs than any other category. Then there is a second most activated category, and a third, and so on, down to a long tail of Target categories with only one Target input each.

Using the Targeting algorithm, the botmaster can have quite an enjoyable afternoon building his bot by “filling up lingusitic targets” and accumulating category-count points. To use the Targeting algoritm, the botmaster first selects the conversation logs for analysis. Then by choosing the “Find Targets” option, the botmaster generates a list of Target categories, each with a link to the associated Target inputs. The program provides a direct link from the Target inputs to the Pandorabots Training section, so that the botmaster can efficiently move from Targets to writing new categories.

: The basics: Table of Common forms

2009-03-27T07:52:00.000-07:00

In writing AIML response templates, certain forms of <srai> responses occur over and over again. They are common enough to be worth identifying and naming them. The following table summarizes the four basic types of common <srai> templates: the Synonym, Simple Wildcard, Multiple Wildcard and Divide and Conquer forms.

Synonym form:

<srai>PHRASE</srai>

Simple Wildcard forms:

<srai><star/></srai>

<srai>PHRASE <star/></srai>

<srai><star index="2"/></srai>

Multiple Wildcard forms:

<srai><star/> <star index="2"/></srai>

<srai><star/> PHRASE <star index="2"/></srai>

Divide and Conquer forms:

<srai><star/></srai>. <srai><star index="2"/></srai>

<srai>PHRASE1 <star/></srai>. <srai>PHRASE2 <star index="2"/></srai>

: The basics II: Simple wildcard reductions

2009-03-26T12:22:00.000-07:00

AIML uses a wildcard * (the star character) to stand for one or more words. An AIML pattern such as <pattern>I AM *</pattern>, taken by itself, matches a wide range of inputs such as "I am tired", "I am reading a book", "I am waiting for a reply" and so on. If the input is "I am tired", the wildcard is said to be bound to the word "tired" (1 word). If the input is "I am reading a book", the wildcard is bound to "reading a book" (3 words), and similarly, if the input is "I am waiting for a reply", the wildcard is bound to "waiting for a reply" (4 words).

Inside the template, AIML uses the <star/> tag to access wildcard bindings.

Trivially, the category

<category>
<pattern>*</pattern>
<template><star/></template>
</category>

will just echo the client's input:

Human: Hello!
Robot: Hello!
Human: Who are you?
Robot: Who are you?

The simplest form of AIML reduction using <srai> together with <star/>, involves reducing or simplifying the input by one or a few words:

<category>
<pattern>I AM ESPECIALLY *</pattern>
<template><srai>I AM <star/></srai></template>
</category>

If someone says, "I am especially tired", or "I am especially interested in this book", it is really no different logically from saying "I am tired" or "I am interested in this book". A philosopher might say, the word "especially" plays no logical role in the sentence. More practically, the bot may have a reply for "I am tired" and "I am interested in something", so reducing the input by removing the
word "especially" will link these inputs to appropriate responses.

The categories:

<category>
<pattern>I AM TIRED</pattern>
<template>Maybe you should take a nap?</template>
</category>

<category>
<pattern>I AM ESPECIALLY *</pattern>
<template><srai>I AM <star/></srai></template>
</category>

produce the dialog:

Human: I am especially tired.
Robot: Maybe you should take a nap?

As a bonus, these types of reduction categories can reduce a sentence with "I am" followed by any number of occurrences of "especially":

Human: I am especially especially especially tired.
Robot: Maybe you should take a nap?

A slightly related, also very common form of reduction, eliminates sequences of words (clauses) that can be eliminated from the input without changing its meaning significantly. Such clauses are decoration, added by the human personality, perhaps as social conventions, but again, the philosopher might say they have no logical purpose. "I will state that I warned you about his condition" is really the same as "I warned you about his condition", at least as far as the robot is concerned. The robot may already have a response to "I warned you about something", so by reducing the input, the bot stands a better chance of making an intelligent sounding reply.

In these cases we use a <pattern> with a wildcard, but end up throwing away all the words in the pattern except for the wildcard:

<category>
<pattern>I WILL STATE THAT *</pattern>
<template><srai><star/></srai></template>
</category>

Another example is a category for inputs that start with "At any rate..."

<category>
<pattern>AT ANY RATE *</pattern>
<template><srai><star/></srai></template>
</category>

A last example handles sentences that begin "I assure you that..."

<category>
<pattern>I ASSURE YOU THAT *</pattern>
<template><srai><star/></srai></template>
</category>

: The basics I: Linking Synonyms

2009-03-26T11:50:00.000-07:00

The simplest form of category in AIML is one with an atomic pattern, namely, a pattern with no wild cards.

For example

<category>
<pattern>NAME</pattern>
<template>My name is ALICE.</template>
</category>

produces the dialog:

Human: Name?
Robot: My name is ALICE.

But there are many different ways of asking for a name. "What is your name?", "Who are you?", "Tell me your name", "Do you have a name?", "Your name is?" are all synonyms for "Name?".

In AIML we link all of these synonyms together using the <srai> tag.

The category:

<category>
<pattern>WHAT IS YOUR NAME</pattern>
<template><srai>NAME</srai></template>
</category>

used in conjunction with the category above, produces the dialog:

Human: What is your name?
Robot: My name is ALICE.

Similarly, we can add categories such as:

<category>
<pattern>DO YOU HAVE A NAME</pattern>
<template><srai>NAME</srai></template>
</category>

and

<category>
<pattern>YOUR NAME IS</pattern>
<template><srai>NAME</srai></template>
</category>

and so on for all the variations of "Name?"

Creating a new chat bot involves writing an enormous amount of original AIML content. Because of its minimalism, AIML lets the botmaster approach content creation one small step at a time. Typically when creating a bot, we identify in the chat logs a new variation of an input we have already seen before. For example, we might see "I want to know your name", and realize there is already a response for this. The convenience of <srai> is that we don't have to go searching through files and files of code to find the response. We know the response is already in there somewhere, so we can just link to it with <srai>:

<category>
<pattern>I WANT TO KNOW YOUR NAME</pattern>
<template><srai>WHAT IS YOUR NAME</srai></template>
</category>

Notice that we linked to WHAT IS YOUR NAME. This doesn't matter, because there is already another category linking WHAT IS YOUR NAME to NAME.

As a general rule of thumb, a good design principle of AIML is to follow the rule that each <srai> should "shorten" then input. In this case that means that reducing WHAT IS YOUR NAME (4 words) to NAME (1 word) is ok, and reducing I WANT TO KNOW YOUR NAME (6 words) to WHAT IS YOUR NAME (4 words) is ok, but we should avoid categories like:

<category>
<pattern>TELL ME YOUR NAME</pattern>
<template><srai>I WANT TO KNOW YOUR NAME</srai></template>
</category>

By avoiding such designs, the AIML program is guaranteed to terminate, and we will never see the "Too much recursion in AIML" error. Why this is, will be explained in more detail later. For now, keep in mind the design rule that in AIML, it is better to store actual responses along with the simplest and shortest possible patterns. That is why putting the response "My name is ALICE" inside the category with pattern NAME, is better than putting it with WHAT IS YOUR NAME.

Turing Test Cartoons

2009-03-25T11:23:00.000-07:00

We've been collecting Turing Test-related cartoons found online.

http://www.thinkin-lincoln.com/index.php?strip_id=857

http://ars.userfriendly.org/cartoons/?id=20041003

http://dilbert.com/strips/comic/2009-03-16/

http://xkcd.com/329/

Please let us know if you find any more.

New AIML Learning File

2009-03-10T11:53:00.001-07:00

AIML Botmaster Steve Worswick (Square Bear) has written a file that will allow users to teach your bot new facts rather than just correcting its replies using badanswer.aiml. The user should say LEARN then the fact. For example:

Human: Learn the sun is hot
Bot: Ok I will learn that the sun is hot.

Human: Learn London is in England
Bot: Ok I will learn that London is in England.

Human: Learn a cat has four legs.
Bot: Ok I will learn that a cat has 4 legs.

Human: What has 4 legs?
Bot: a cat.

Human: What is the sun
Bot: hot.

Human: Learn the sun is hot and yellow
Bot: Ok I will learn that the sun is hot and yellow.

Human: What is hot and yellow
Bot: the sun.

Human: What is the sun
Bot: hot and yellow.

Human: Where is London
Bot: in England.

Human: What is in England
Bot: London.

Human: Learn Dr Wallace is an AI expert
Bot: Ok I will learn that Dr Wallace is an AI expert.

Human: What is an AI expert
Bot: Dr Wallace.

Human: Who is an AI expert
Bot: Dr Wallace.

Human: Who is Dr Wallace
Bot: an AI expert.

Human: What is hot
Bot: the sun.

Human: What has a cat?
Bot: 4 legs.

Square-Bear will update this file to cover more complicated knowledge such as "Learn the 2012 Olympic Games will be held in London", "Where will the 2012 Olympic Games be?". The current version of the file is available, along with all my other public AIML files at: http://square-bear.co.uk/aiml Square-Bear says, "Feel free to use it in your bots!"

McKinney Agency Launches Chat Bot

2009-02-24T13:36:00.000-08:00

The ad agency McKinney.com has launched a new web site that mashes a variety of advanced technologies including an AIML chat bot. McKinney is one of the top ten advertising agencies in the US. Working in partnership with Othersource, McKinney has been developing the site for the past 9 months.

It's a site you can talk to. You can type questions in natural language, the site will answer and show you different parts of its content. So McKinney.com is one of the first examples of web 3.0 - it adapts to you, rather than the other way around. The site looks beautiful, too, and most of it is in 3D. Have a look for yourself: http://mckinney.com/

Program O on Sourcefourge

2009-02-16T17:54:00.000-08:00

This week Elizabeth Perreau placed Program O under the GNU General Public License (same as Linux) on Sourceforge. Program O allows you to host a chatbot on your website using in PHP with MySQL. If you would like a demo or more information please visit http://www.program-o.com.

The Specifications for Program O:

Database Environment : MySql
Development Status : 4 - Beta
License : GNU General Public License (GPL)
Programming Language : PHP
Topic : Intelligent Agents
User Interface : Web Based

The AIML botmaster may consider Program O as an alternative to the now unsupported Program E, an earlier AIML interpreter in PHP.

Simple AIML Editor

2009-01-22T10:56:00.000-08:00

Adeena Mignogna has written a new AIML editor, simply called, "Simple AIML Editor". Adeena said she got a little frustrated with the choices out there to manage her AIML
file content, so she wrote a new AIML editor.

The SAE is the latest development in the evolution of spreadsheet-style AIML editors like GaitoBotEditor and the Ai-Dealer AIML Spreadsheet editor. The SAE has simplified the interface and reduced the number of operations to a few, common botmaster tasks.

One of the challenges in managing AIML is that, although the AIML is in XML format, the data is a hybrid of highly structured, row-oriented fields (file name, pattern, that, topic, pattern, template) combined with hierarchical XML data in the template. The large amount of row-oriented data makes it hard to edit AIML with off-the-shelf XML editors. The spreadsheet seems to be the best metaphor to manage the large number of AIML categories found in convincing A.I. bots. Then other tools, at minimun a text editor, such as provided by the SAE, are required to edit the AIML template-side responses.

The SAE also allows the botmaster to load an XML schema to check for valid AIML. The editor supports file character encodings utf-8 and iso-8859-1. The editor also includes a "comment manager" to help the botmaster store comments and copyright statements at the head of each AIML file.

The editor is a C# application written for Windows. The program has been tested on both Windows XP and Vista machines and it seems to run fine on both of them.

Adeena would appreciate any feedback on the application and would definitely like to know if anyone experiences any problems with it.

The Simple AIML Editor can be found here:
http://riotsw.com/sae.html

Program O

2009-01-14T13:00:00.000-08:00

Elizabeth Perreau, creator Shakespearebot, has written a new AIML interpreter. In keeping with the tradition of naming AIML interpreters with letters of the alphabet (Program B, Program C, Program D etc.) Elizabeth has chosen to name hers Program O (the letter O, pronounced "Oh"). Like the no longer actively supported Program E, Program O is based on PHP and MySQL. You can check out Program O at http://www.program-o.com.

Program E has some well known bugs, and without active support, it can be frustrating to try to make modifications to its source code. Elizabeth says, "I just got to the stage where if I wanted to get into AIML more I had to re-write alot of it for my needs." Program O is written to make it easy to add new AIML tags and extensions. Elizabeth has already implemented the custom Pandorabots tags <eval> and <learn> for client-based bot training.

Program O is set for release on March 1, 2009. Meanwhile you can help Elizabeth debug the code by visiting the site and chatting with her bot.

ALICE and AIML videos on Youtube

2008-12-27T21:15:00.000-08:00

There are some fun ALICE and AIML demo videos popping up on Youtube. This first one is an example of using voice recognition and speech synthesis to create an "interview." Be prepared to wait for some funny animation at the beginning of the video, before the interview starts. Parts of the interview are quite funny and highlight the difficulty of achieving high quality speech recognition.

The next video is another example of speech and voice also combined with a high quality avatar. Listening carefully to the bot's responses, you can hear a few custom responses, and a lot of replies straight out of the original free ALICE bot.

Several projects are underway to embed AIML bots in Second Life. This video shows an example. The bot object uses Linden Scripting Language to communicate with a Pandorabot.

The most popular Pandorabot continues to be the Flash iGod bot.
Several videos have appeared that incorporate chats with iGod. iGod does not represent any particular religion, but the script is based on the version of ALICE that claimed to be a "Protestant Christian".

And as a demonstration that a bot can be trained to follow any religion, watch this video of MuslimBot. Like the God bot, MuslimBot is hosted on Pandorabots.

Santa Bot is Back in Town

2008-11-15T17:49:00.000-08:00

The A.I. Foundation is pleased to announce the 2nd annual re-appearance of the Santa Bot. The Santa bot is based on the Superbot and has a totally unique, new personality tailored to old Saint Nick. The bot brain has no overlap with the A.L.I.C.E. bot. Santa is totally kid-safe and fun for the whole family. For now Santa is free. Tell Santa what you want for Christmas. Have a chat with Santa at http://alicebot.org/Santa/.

Our Santa bot uses an Oddcast/Sitepal avatar with text-to-speech.

Santa bot is still learning. The more you chat with him, the smarter he will become.

MLAI Foundation Re-Launch

2008-11-15T17:18:00.000-08:00

Christopher Doyon (botmaster at mlaifoundation.info) has written to announce that he putting the MLAI Foundation and related sites back online. The MLAI Foundation is the home of several of Christopher's bots, as a forum.

Just in time for Christmas shopping, he has also reactivated the amazing Turing Store. This one of a kind AI and robotics online shop has the best of the best Holiday gift ideas for the MLAI enthusiast on your list. The robots especially this year are astounding.

Check out www.TuringStore.info

Remember that donations to the MLAI Foundation are gratefully accepted. And not just money, they can use any functioning computers that you may have laying around. MLAI can make use of them to host servers and experiments.

GaitoBot AIML-Editor

2008-11-07T15:51:00.000-08:00

Daniel Springwald wrote to tell us two pieces of good news. First, the GaitoBot AIML Editor (*) is now released in final version1.0. This visual AIML editor, good for managing large AIML sets and files, is free and will be in future for free. This means it can be used for private or commercial use without any restrictions and without paying any fees.

The second piece of good news is, they now offer an AIML Chatbot hosting service, which the editor can directly upload to. The botmaster has just to sign in on to the site http://www.gaitobot.de/ and can publish the bot. To put it on his website, the botmaster need only copy and paste an html-snippet. Gaitobot provides free hosting for bots up to a size of 256kb. For a bot with a bigger knowledge, the company charges a small fee.

(*) The Gaitobot editor is virus and spyware tested by several checks local and online -for example by suggestsoft.com.

You can find a report here:

http://www.suggestsoft.com/soft/springwald-software-entwicklung/gaitobot-aiml-editor/report1.html

http://www.suggestsoft.com/soft/springwald-software-entwicklung/gaitobot-aiml-editor/report2.html

The program is also signed as created by a known developer and so it shouldnot show the warning "unkown manufacturer" while installing.

InfraDrive to sponsor Chatterbox Challenge 2009

2008-10-06T15:04:00.000-07:00

Ehab El-agizy, founder of InfraDrive and developer of the RoboMatic X1 chatbot, has announced that InfraDrive will sponsor the Chatterbox Challenge (CBC) in 2009. Founded by Wendell Cowart in 2001, the Chatterbox Challenge is a performance test for chat bots. Unlike the popular Loebner Prize Contest, the bots compete online in the CBC. Also unlike the Loebner contest, the CBC has awarded prizes for bot performance in multiple categories. ALICE has won awards in several categories of the CBC including Top 10 (2001-2008), Most Popular (2004, 2006), Best Character/Personality (2005), Most Knowledgable (2004), and overall Contest Winner (2004).

Ehab is currently collecting a database of bots and botmasters who want to participate in the 2009 contest. You can post your entry to http://forums.chatterboxchallenge.com/viewtopic.php?f=5&t=2

Some new Jokes in AIML

2008-09-11T08:48:00.000-07:00

Thanks to a post to Dirk Scheuring to the Robitron mailing list, I leaerned about a Lisp program that generates jokes of the form, "What do you get when you cross X with Y?":

http://grok-code.com/12/how-to-write-original-jokes-or-have-a-computer-do-it-for-you/

Example joke:

WHAT DO YOU GET WHEN YOU CROSS A DANCE WITH A LEMON?

sour balls

I tweaked the Lisp program to output AIML, so you can include the jokes in chat bots like A.L.I.C.E.

Human: tell me a joke

JOKER: WHAT DO YOU GET WHEN YOU CROSS A CAT AND A LEMON?

Human: What?

JOKER: sour puss.

Human: tell me a joke

JOKER: WHAT DO YOU GET WHEN YOU CROSS A BUG AND A RELATIVE?

Human: what

JOKER: ant.

etc.

AIML:

<li>WHAT DO YOU GET WHEN YOU CROSS A MURDERER AND FROSTED FLAKES?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A COUNTRY AND AN AUTOMOBILE?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A CHEETAH AND A HAMBURGER?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS FINALS AND A CHICKEN?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A RABBIT AND A LAWN SPRINKLER?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS AN EXCITED ALIEN AND A CHICKEN?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS AN ALIEN AND A CHICKEN?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS MUSIC AND AN AUTOMOBILE?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS SOUR MUSIC AND AN ASSISTANT?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS MUSIC AND AN ASSISTANT?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A SERIOUS THIEF AND A MAD YOUNG MAN?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A SERIOUS THIEF AND A CRAZY RABBIT?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A POPPY AND ELECTRICITY?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A DANCE AND A CHEETAH?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A DANCE AND A LEMON?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A PORT AND FROSTED FLAKES?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A PORT AND A MURDERER?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A BANK AND A SKUNK?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A DING AND MILK?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A ROAD AND A STRAWBERRY?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A ROAD AND JELLY?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A TOAD AND A GALAXY?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A DOG AND SANDPAPER?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A BUG AND A RELATIVE?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A BAD BUG AND CANNED SAND?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS AN ANT AND A RABBIT?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A CAT AND A PURPLE PERSON?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A CAT AND A KILLER?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A CAT AND A LEMON?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A CAT AND A TUNE?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A CAT AND A BAND?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A PIG AND A NINJA?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A CRAZY COW AND A BANNED PARROT?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A COW AND A LEMON?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS A BAD COW AND A CANNED HAT?</li>

<li>WHAT DO YOU GET WHEN YOU CROSS JAM AND A TROUT?</li>

</random>

</template></category>

<that>* A MURDERER AND FROSTED FLAKES</that>

<template>cereal killer.</template>

</category>

<that>* A COUNTRY AND AN AUTOMOBILE</that>

<template>carnation.</template>

</category>

<that>* A CHEETAH AND A HAMBURGER</that>

</category>

<that>* FINALS AND A CHICKEN</that>

</category>

<that>* A RABBIT AND A LAWN SPRINKLER</that>

<template>hare spray.</template>

</category>

<that>* AN EXCITED ALIEN AND A CHICKEN</that>

<template>eggs-cited eggs-traterrestrial.</template>

</category>

<that>* AN ALIEN AND A CHICKEN</that>

<template>eggs-traterrestrial.</template>

</category>

<that>* MUSIC AND AN AUTOMOBILE</that>

<template>cartune.</template>

</category>

<that>* SOUR MUSIC AND AN ASSISTANT</that>

<template>bandaide and lemonaide.</template>

</category>

<that>* MUSIC AND AN ASSISTANT</that>

<template>bandaide.</template>

</category>

<that>* A SERIOUS THIEF AND A MAD YOUNG MAN</that>

<template>boycrazy grave robber.</template>

</category>

<that>* A SERIOUS THIEF AND A CRAZY RABBIT</that>

<template>hopping mad grave robber.</template>

</category>

<that>* A POPPY AND ELECTRICITY</that>

<template>flower power.</template>

</category>

<that>* A DANCE AND A CHEETAH</that>

<template>fastball.</template>

</category>

<that>* A DANCE AND A LEMON</that>

<template>sour balls.</template>

</category>

<that>* A PORT AND FROSTED FLAKES</that>

<template>I don't know, but it's serial.</template>

</category>

<that>* A PORT AND A MURDERER</that>

<template>serial killer.</template>

</category>

<that>* A BANK AND A SKUNK</that>

<template>dollars and scents.</template>

</category>

</category>

<that>* A ROAD AND A STRAWBERRY</that>

<template>traffic jam.</template>

</category>

<that>* A ROAD AND JELLY</that>

<template>traffic jam.</template>

</category>

<that>* A TOAD AND A GALAXY</that>

<template>star warts.</template>

</category>

<that>* A DOG AND SANDPAPER</that>

</category>

<that>* A BUG AND A RELATIVE</that>

</category>

<that>* A BAD BUG AND CANNED SAND</that>

<template>banned band.</template>

</category>

<that>* AN ANT AND A RABBIT</that>

<template>bugs bunny.</template>

</category>

<that>* A CAT AND A PURPLE PERSON</that>

<template>purrr-ple purrr-son.</template>

</category>

<that>* A CAT AND A KILLER</that>

<template>mew-rderer.</template>

</category>

<that>* A CAT AND A LEMON</that>

</category>

</category>

</category>

<that>* A PIG AND A NINJA</that>

<template>pork chops.</template>

</category>

<that>* A CRAZY COW AND A BANNED PARROT</that>

<template>canned carrot.</template>

</category>

<that>* A COW AND A LEMON</that>

</category>

<that>* A BAD COW AND A CANNED HAT</that>

<template>banned cat.</template>

</category>

<that>* JAM AND A TROUT</that>

<template>jellyfish.</template>

</category>

A.L.I.C.E. selected for Loebner Prize 2008 finals

2008-08-05T09:07:00.000-07:00

Out of thirteen entries, the following systems have been selected, through the preliminary phase, to compete in the finals for the 2008 Loebner Prize for Artificial Intelligence:

Alice by Richard Wallace

Brother Jerome by Peter Cole & Benji Adams

Elbot by Fred Roberts

Eugene Goostman by Vladimir Veselov

Jabberwacky by Rollo Carpenter

Ultra Hal by Robert Medeksza

Congratulations to the finalists and also to the other contestants for their outstanding effort. Looks like quite a line up this year, with six previous entries and three previous Bronze medal winners. All are very serious, long-term projects. I hope someone tells the press about this.

Saying a list of AIML responses in order

2008-07-17T09:58:00.001-07:00

Here is a good question that came in about AIML style:

Question:
I use the <random> tag in AIML when I have a list of responses. But instead of saying the responses randomly, is there any way I can get the bot to say them in a specific order? For example, I have four responses for one input pattern. Can I get the bot to say them one by one each time that pattern is activated?

Answer:
There is no specific tag for that in AIML, but it is not too hard to implement using existing AIML tags. In this example, the input xxx results in "Response One" the first time it is entered, "Response Two" the second time, "Response Three" the third time, then "Response Four", then cycles back to "Response One."

The program uses the AIML variable "state" to keep track of which response is next. Some categories are provided to implement a "successor" function to advance the state variable through I, II, III, IV and back to I.

<aiml version="1.0">

<category>
<pattern>xxx</pattern>
<template>

<think>
<set name="state">
<srai>SUCCESSOR <get name="state"/></srai>
</set>
</think>
<srai>say response <get name="state"/></srai>

</template>
</category>

<category><pattern>SUCCESSOR</pattern>
<template>I</template>
</category>
<category><pattern>SUCCESSOR *</pattern>
<template>I</template>
</category>
<category><pattern>SUCCESSOR I</pattern>
<template>II</template>
</category>
<category><pattern>SUCCESSOR II</pattern>
<template>III</template>
</category>
<category><pattern>SUCCESSOR III</pattern>
<template>IV</template>
</category>
<category><pattern>SUCCESSOR IV</pattern>
<template>I</template>
</category>

<category>
<pattern>SAY RESPONSE I</pattern>
<template>Response One.</template>
</category>

<category>
<pattern>SAY RESPONSE II</pattern>
<template>Response Two.</template>
</category>

<category>
<pattern>SAY RESPONSE III</pattern>
<template>Response Three.</template>
</category>

<category>
<pattern>SAY RESPONSE IV</pattern>
<template>Response Four.</template>
</category>

<category>
<pattern>SAY RESPONSE *</pattern>
<template>Undefined.</template>
</category>

</aiml>

Loebner Prize 2008 Draws 13 Entries

2008-06-03T10:06:00.000-07:00

The following thirteen entries are entered into the preliminary phase of the 2008 Loebner Prize for Artificial Intelligence:

Zeta by Jeremy Gardiner
Elbot by Fred Roberts
Eugene Goostman by Vladimir Veselov
Orion by Adeena Mignogna
LQ by Qiong John Li
Brother Jerome by Peter Cole & Benji Adams
Chip Vivant by Mohan Embar
Jabberwacky by Rollo Carpenter
Alice by Richard Wallace
Botooie by Elizabeth Perreau
Amanda by Simon Edwards
Ultra Hal by Robert Medeksza
trane by Robert Scott Mitchell

Three of this years entries areprevious Loebner winners and two of them multi-year winners. Two of the entries this year use AIML: Orion by Adeena Mignogna and our own ALICE bot.

Actionscript 3 Pandorabot Chat Class

2008-05-31T10:07:00.000-07:00

Pandorabots has an XML-RPC interface that allows botmasters to link the A.I. chat bot to third party applications such as SMS, Second Life and Flash. Flash James Durrant, released a free script to integrate Pandorabots with Flash Actionscript 2. Now with Actionscript 3 becoming so widely adopted, another programmer, Marcus Dickinson, has updated Jamie's old Flash Chat interface into something more current.

Marcus announced these new features in his AS3 script:

One line implementation - You can get a basic Flash Chat Pandorabot going by filling in the "yourbotid" and "Common Bot Name" arguments in this one line of code:

var botChat:Chat = new Chat("yourbotid","Common Bot Name",stage.stageWidth/2,stage.stageHeight/1.3, 85, false);

Drag - The topbar is draggable like any other application window.

Close Button - Want users to stay on your site but able to turn the chatbot off? There's a handy close button for that.

Typing Speed - A simple variable (85 up above), that controls the typing speed of your robot. Want it to respond more slowly or quickly? Adjust that. Anyway, there are a lot more subtle things in the class as well, and I hope you enjoy it.

You can download the necessary files at http://www.diariesofwar.com/downloads/AS3Chat.zip

Finally, Marcus says, "Help me get my own Superbot, make a paypal donation to waarangel@gmail.com"

Program E Bug Fix

2008-05-28T08:06:00.000-07:00

This is the fix we found for the bug we reported in Program E.

I am working with a developer who knows PHP well but not too much AIML. I know AIML but not much PHP. He found something in the code that apparently fixes the bug, at least in the tests we have done. I don't know if anyone is officially maintaining Program E at the moment, but anyone working with the code may be able to check this solution.

By the way, we are using version 0.8 of Program E.

Here is what he said:

Dr. Wallace, this is piece of code which was changed by me. The only line I added is highlighted below.

This code is executed when no match is found by the “graphwalker”.

As graphwalker searches for matches it adds words matched by the “*” wildcard to $inputstarvals.

But when it reaches it the end of the input and finds no matches it should clear $inputstarvals reference and return back to the root of the tree.

// Else no match found...

if ((($whichresult[0]==-1)&&($whichresult[1]==-1)&&($whichresult[2]==-1))||($continuenode==1)) {

//If we were most recently on a wildcard (*,_) then we are still matching it.

if (($onwild==1)&&($word!="")&&($word!="")&&($word!="")){

debugger("On wild and in *. keep going with graphwalker.",2);

addtostar($parton,$word,$inputstarvals,$thatstarvals,$topicstarvals,2);

return graphwalker($remains,$parent,1,1,$parton,$inputstarvals,$thatstarvals,$topicstarvals,$patternmatched);

}

else {
//We didn't find anything. We need to come back out

$inputstarvals=array();

debugger("Result is blank from query in *. Returning blank",2);

return "";

}

Attached is the latest (Program E 0.9) version of this script. We use version is 0.8. This code should work the same way in the latest version. Changes which were introduced between 0.8 and 0.9 are not related to this piece of code.

Program E Bug

2008-05-28T07:50:00.000-07:00

We found a bug in the Program E AIML interpreter and discovered a possible workaround. This post describes the bug; we will publish the solution in a subsequent post.

Suppose you create a simple default category:

<category>
<pattern>*</pattern>
<template>Keywords: <star/></star>
</template>

Assuming there is no other AIML, this category will just echo
whatever you type:

Client: Hello there
Bot: Keywords: Hello there
Client: testing one two three
Bot: Keywords: testing one two three

Now add a second AIML category,

<category>
<pattern>_ TEST ME *</pattern>
<template><srai>TEST ME</srai></template>
</category>

We get the expected result:

Client: xxx test me xxx
Bot: Keywords: TEST ME

Ok, finally, add one more category:

<category>
<pattern>TEST * ME</pattern>
<template>TEST ME</srai></template>
</category>

Now it is messed up:

Client: test xxx me
Bot: ME

What happened to the "TEST"?
and even the one that worked before is broken:

Client: xxx test me xxx
Bot: ME

If we copy the same AIML test file over to Pandorabots:

Client: test xxx me
Bot: TEST ME
Client: xxx test me xxx
Bot: TEST ME

Vote for A.L.I.C.E.!

2008-04-26T14:33:00.001-07:00

The 2008 Chatterbox Challenge judges have selected A.L.I.C.E. as the #1 chatter bot in preliminary scoring! Now it is your turn to vote for the best of the bots. The judges have selected the top 20 bots, and the Chatterbox Challenge is open to public voting. Whether you vote for A.L.I.C.E. or not, you will be amazed by the variety and quality of bots competing in this year's contest.
Unlike the famous Loebner Prize contest, the Chatterbox Challenge allows entries to be submitted online. So in many cases, you can chat directly with these bots over the web. (The organizers of the Loebner Prize are concerned about cheating.) Also unlike the conventional Turing Test, the Chatterbox Challenge does not directly compare human and bot performance; it is a ranking of the bots on their own merits.
If you do choose to vote for A.L.I.C.E., we appreciate your support!

How to compare two variables in AIML

2008-04-25T14:48:00.000-07:00

Steve Worswick (Square-Bear) has done something amazing. In AIML, there is no obvious way to compare to variables (or predicates, as they are called in AIML). But with a clever use of the Pandorabots AIML extensions and , Steve has come up with a way to compare to variables.

Pandorabots implemented and in order to help botmasters write scripts for their bots to learn new AIML categories from conversations. Steve has discovered that these extensions can also be used to create a dynamic extension to the language, that allows the botmaster to compare two variables.

Suppose the botmaster wants to compare two predicates with the values JOHN and PAUL.
The basic "trick" behind Steve's method is to "learn" a new category like

<category>
<pattern>BOTCHECK JOHN</pattern>
<template>
<think>
<set name="match">YES</set>
</think>
</category>

The comparison uses symbolic reduction to test <srai>BOTCHECK PAUL</srai>. This does not match the newly learned categroy with the pattern BOTCHECK JOHN. It does however match another category:

<category>
<pattern>BOTCHECK *</pattern>
<template>
<think><set name="match">NO</set> </think>
</category>

Only the input BOTCHECK JOHN will match the first category, in which case the predicates have the same value. The AIML Steve developed is a little more complicated than that, and you can find out all the details in his post to the mailing list.

You can download the free AIML variable comparison set from
http://www.square-bear.co.uk/aiml/botcompare.aiml

Pandorabots mentioned in New Scientist

2008-04-18T15:54:00.000-07:00

The New Scientist Feedback column ran a story about Ron Ingram's Godsbot in the March 22 issue. The article describes the author's interactions with Godsbot, and concludes that it must be based on ELIZA. (Godsbot is, in fact, based on ALICE). The article cites the usual types of good, not-so-good, and humorous bot responses. Despite the obvious limitations, the author is "impressed".

After identifying Ron Ingram as the creator of Godsbot, the authors say "The trail from Godsbot doesn't stop there, either. Feedback has tracked down the source of the AI software, a site called Pandorabots, which lets you design your own software robots and turn them loose on the Internet. When we last checked, the site boasted that Pandorabots had served up 564,580,317 replies. Is it too late to shut the lid?"

German Alice is back online

2008-04-18T14:43:00.000-07:00

Christian Drossmann, creator of the German ALICE bot, has written to say that the German speaking chatbot is back online and hosted at Pandorabots. Christan said he "couldn't resist giving the (Pandorabots) system a try", and he plans to analyze the log files and add more content to the "rather crude" standard categories in German. He said, "I missed the coding."

The bot is accessible via http://www.drossmann.de/

Furthermore, Christian informs us that a German guy developed a Skype-plugin for Program E E, the AIML interpreter in PHP. You can find it at http://blog.kevinkempfer.de/2008/02/12/alice4skype-ist-da/.

The page is in German, but the download links are almost at the top of the page where you will find the hyperlinked words "Windows" and "Linux

For more information about German ALICE, you can contact Christian Drossmann via christian [at] drossmann [dot] de.

Godsbot Free for All

2008-03-10T17:31:00.000-07:00

Botmaster Ron Ingram, long-time AIML developer and author of the Buddhabot, has advanced his bot to create a new version of 'God'. The God personality is consistenty the most popular bot on Pandorabots. Ron's Godsbot is designed with a more Christian perspective. As well as releasing the bot, Ron has created a blog dedicated to his fascinating ideas. Here is what Ron had to say about the creation of Godsbot, in his own words:

First I cloned my Buddhabot; a bot that I have been working on for several years initially developed by manually manipulating and customizing all of the original ALICE files in excel (if I were recreating Buddhabot today I probably would have started with the Superbot program but this was not available to me in2004). For more information on the evolution of Buddhabot go to Buddhabots.com and read the "News" tab which provides a list of the new AIML files and content as they were added. All of these subsequent AIML files were built in excel, copied into a textfile, renamed with an .aiml extension and then uploaded to Pandorabots.com.

Second, I modified the original Buddhabot properties to reflect a Christian perspective.

Third, I created some new Christian aiml files in excel using the same procedure as described in item 1 above.

Fourth, I created a blog that provides information on the mission and purpose behind this project.

This last point is where I think some botmasters maybe missing an opportunity. I think every bot needs a personality and a purpose. When we first meet a human, we aim to find points of relation (who, what, and where). We seek to determine a name, where the person is from, and so on, building up relational probabilities. Then the fun really begins as we start trying to learn who someone really is but normally we have little interest in discovering much about a stranger on the street unless we identify a striking commonality. Likewise with a bot, I believe we need to create a persona and a platform based on something sincere and authentic that we (and the bot) can be passionate about. This is how we may begin to go beyond novelty and gimmick and begin to establish a"real" persona capable of sustaining longer conversations and developing relationships.

The purpose of godsbot is two-fold:

* to advance interest in peaceful relations among people of faith; and,

* to attract donations so I can spend more time doing what I love (AI research and development).

Good luck and stop by for a free chat with Godsbot at godsbot.org.

Time and Effort to Create a Unique Bot Personality

2008-03-07T15:50:00.000-08:00

The free A.L.I.C.E. bot contains about 120,000 AIML categories, the category being the basic unit of knowledge in AIML. A category is essentially one question-and-answer stimulus-response pair. Anyone is free to use the open source A.L.I.C.E. brain as the basis for his bot, but for commercial applications, the A.L.I.C.E. content may be inappropriate. A.L.I.C.E. contains many "humorous" and politically-incorrect responses designed to make her personality more believable, but these responses are undesirable for a bot representing a corporation. Even many entertainment applications require responses quite different than A.L.I.C.E.'s.

Although the A.L.I.C.E. bot has 120K categories, not as many are required to create a believable bot personality. From our experience a bot with 10,000 AIML categories will create a believable illusion of intelligence. That is why we created the Superbot AIML set, essentially a list of the top 10,000 most-activated AIML categories with blank responses. The process of creating a unique, proprietary bot personality can be reduced to essentially "filling in the blanks" of the Superbot data.

A good AIML botmaster can write about one AIML category per minute. This is not to say that every AIML category takes 1 minute to write. Some categories require a lot of thought and could take up to 30 minutes to create. In other cases, many hundreds of categories can be created by "cut and paste" in less than a minute. But overall, an average of about 1 per minute is reasonable in our experience.

10,000 categories at the rate of 1 per minute is about 7 days of time, working 24 hours a day. A more practical scenario, with rest periods included, is two or three proficient AIML botmasters working over a one or two month period. Those wishing to create a totally unique, proprietary bot personality, should take into account the cost of hiring these consultants.

A word on AIML content: there is no magic A.I. engine that can translate domain-specific knowledge into AIML. Suppose you want a bot that talks about your brass fitting business. It is certainly possible to create an AIML bot that answers all the most common questions about brass fittings. You may even have a FAQ or Wiki with much of this knowledge already encoded. You can train an AIML bot to talk about anything, but it is a painstaking process that takes time, depending on how familiar the botmasters are with the domain. If the botmaster knows nothing about the brass fitting business, and you are an expert, it may be easier for you to learn AIML than to teach the botmaster the brass fitting business. In many such cases it is more cost effective to teach domain experts AIML, than to hire AIML consultants and teach them the domain knowledge.

ELIZA pioneer Joseph Weizenbaum dies

2008-03-07T13:01:00.001-08:00

Joseph Weizenbaum, MIT professor, co-founder of Computer Professionals for Social Responsibility, and creator of the famous ELIZA psychotherapist program, died at his home in Berlin at age 85, according to EE Times. The ELIZA program is the ur-chatbot from which A.L.I.C.E. and nearly all other chatbot programs are descended. ELIZA introduced the concepts of stimulus-response, pattern matching, and pronoun transformation to natural language processing. Remarkably, Weizenbaum was reportedly "shocked" that MIT students and staff anthropomorphised the simple program. They revealed personal information to the bot in online chats. In response, Weizenbaum spent much of the rest of his career as a critic of computer science in general, and artificial intelligence in particular.

Many others also said that the ELIZA program was not a serious development in natural language processing, and it was derided as a 'toy'. By the late 1990's however it became apparent that massive case-based pattern matching was a practical method for achieving lifelike human-computer conversations, essentially the same techique as ELIZA on a bigger scale. All chat bot developers, not just those of us using AIML, owe a debt of gratitude to the pioneering work of Prof. Weizenbaum.

Square-Bear's New AIML Repository

2008-03-04T14:11:00.000-08:00

One of our most prolific AIML botmasters, Square-Bear, has devoted a web page to his AIML creations. Square-Bear has developed many new games and AIML applications that point us in the direction of the "Star Trek-style talking computer of the future." Some of Square-Bear's creations include:

Drphil.aiml - A personality test converted to AIML.

Horoscope.aiml - Random horoscope fortune-telling in AIML.

Yomama.aiml - A collection of "yo mamma" type jokes for when the user starts insulting the bot's mother.

You can download these free files, and many more, from http://square-bear.co.uk/aiml/

Parsing the Turing Test: Book Published

2007-12-24T15:16:00.000-08:00

Six years in the making, the book Parsing the Turing Test has finally been published by Springer Netherlands. The book, edited by Robert Epstein, Gary Roberts and Grace Beber, is an impressive collection of 29 chapters by various authors on, as the subtitle says, "Philosophical and Methodological Issues in the Quest for the Thinking Computer."

The sponsor of the real-world Turing Test, Hugh Loebner, contributed a chapter, as did prior winners of that prize Thomas Walen, Robby Garner, Jason Hutchins, Richard Wallace and Kevin Copple. Philosophical chapters were contributed by such luminaries as John Searle, Noam Chomsky, Paul Churchland and Jack Copeland. Turing's original 1950 paper on the Imitation Game is reprinted as well.

This book, which also includes a contribution from the late Chris McKinstry, brings together philosophical and practical ideas for passing the Turing Test. Or if not passing it, placing the Test in a historical, philosophical and engineering context. No other work has merged the wide variety of today's Turing Test constituency

Browse the abstracts or order the book at: http://www.springerlink.com/content/r42614/

Note: although the author of this blog contributed a chapter to the book, we receive no royalties or affiliate payments for its publication.

Multiple Keywords in AIML

2007-12-24T14:16:00.000-08:00

Have you ever wanted to convert an FAQ question to AIML, only to be confounded by the overly specific wording of the FAQ question?

For example,

Q: How do I unsubscribe from the email?
A: Unsubscribe and change preferences at http://list.pandorabots.com/mailman/listinfo/pandorabots-general

Most of us are familiar with the four AIML category approach to recognizing single keywords in the input:

<category><pattern>UNSUBSCRIBE</pattern>
<template>Unsubscribe and change preferences at
http://list.pandorabots.com/mailman/listinfo/pandorabots-general
</template>
</category>
<category><pattern>_ UNSUBSCRIBE</pattern>
<template><srai>UNSUBSCRIBE</srai></template>
</category>
<category><pattern>_ UNSUBSCRIBE *</pattern>
<template><srai>UNSUBSCRIBE</srai></template>
</category>
<category><pattern>UNSUBSCRIBE *</pattern>
<template><srai>UNSUBSCRIBE</srai></template>
</category>

But in many cases, the single keyword approach is too general. There may be a comepting FAQ question that uses the same keyword, such as "How do I unsubscribe a bot?" To make the input match more specific, we would often like to use a pair of keywords.

To make the bot respond to a wide set of variations of the input, we would like it to give the same answer to any input that contains the keywords. In this example, the two keywords might be "UNSUBSCRIBE" and "EMAIL". We would like the bot to give the same answer to any input that contains this pair of keywords, inlcuding for example "I want to unsubscribe from email," "Unsubscribe me from email," and "Email unsubscribe."

To accomplish this in AIML, we use a base category and a set of symbolic reductions, just as in the case of the single keyword match. The base category uses a simple pattern containing just the keywords:

<category>
<pattern>UNSUBSCRIBE EMAIL</pattern>
http://list.pandorabots.com/mailman/listinfo/pandorabots-general
</template>
</category>

Generally speaking, when dealing with a long, very specific FAQ question, it is better to try to summarize the input pattern in one to three keywords. This makes writing symbolic reductions easier and less error prone.

In our example, the symbolic reductions include combinations of the keyword and wildcards. For each pair of keywords ordered ("UNSUBSCRIBE", "EMAIL") and ("EMAIL", "UNSUBSCRIBE") There are 7 combinations of keywords with at least one wildcard. There is one extra category to reduce the atomic pattern "EMAIL UNSUBSCRIBE" to "UNSUBSCRIBE EMAIL":

<aiml>
<category><pattern>_ UNSUBSCRIBE * EMAIL *</pattern>
<template><srai>UNSUBSCRIBE EMAIL</srai></template></category>
<category><pattern>_ UNSUBSCRIBE * EMAIL </pattern>
<template><srai>UNSUBSCRIBE EMAIL</srai></template></category>
<category><pattern>_ UNSUBSCRIBE EMAIL *</pattern>
<template><srai>UNSUBSCRIBE EMAIL</srai></template></category>
<category><pattern>_ UNSUBSCRIBE EMAIL </pattern>
<template><srai>UNSUBSCRIBE EMAIL</srai></template></category>
<category><pattern> UNSUBSCRIBE * EMAIL *</pattern>
<template><srai>UNSUBSCRIBE EMAIL</srai></template></category>
<category><pattern> UNSUBSCRIBE * EMAIL </pattern>
<template><srai>UNSUBSCRIBE EMAIL</srai></template></category>
<category><pattern> UNSUBSCRIBE EMAIL *</pattern>
<template><srai>UNSUBSCRIBE EMAIL</srai></template></category>
<category><pattern>_ EMAIL * UNSUBSCRIBE *</pattern>
<template><srai>UNSUBSCRIBE EMAIL</srai></template></category>
<category><pattern>_ EMAIL * UNSUBSCRIBE </pattern>
<template><srai>UNSUBSCRIBE EMAIL</srai></template></category>
<category><pattern>_ EMAIL UNSUBSCRIBE *</pattern>
<template><srai>UNSUBSCRIBE EMAIL</srai></template></category>
<category><pattern>_ EMAIL UNSUBSCRIBE </pattern>
<template><srai>UNSUBSCRIBE EMAIL</srai></template></category>
<category><pattern> EMAIL * UNSUBSCRIBE *</pattern>
<template><srai>UNSUBSCRIBE EMAIL</srai></template></category>
<category><pattern> EMAIL * UNSUBSCRIBE </pattern>
<template><srai>UNSUBSCRIBE EMAIL</srai></template></category>
<category><pattern> EMAIL UNSUBSCRIBE *</pattern>
<template><srai>UNSUBSCRIBE EMAIL</srai></template></category>
<category><pattern> EMAIL UNSUBSCRIBE </pattern>
<template><srai>UNSUBSCRIBE EMAIL</srai></template></category>
</aiml>

You can do the same thing with three keywords. For example suppose the FAQ question is "I am still getting Pandorabots email and a I want to unsubscribe." The keywords in this case might be "UNSUBSCRIBE PANDORABOTS EMAIL". This time there are 95 combinations of keyword order and wildcards. Here are the first and last few:

<aiml>
<category><pattern>_ UNSUBSCRIBE * PANDORABOTS * EMAIL *</pattern>
<template><srai>UNSUBSCRIBE PANDORABOTS EMAIL</srai></template></category>
<category><pattern>_ UNSUBSCRIBE * PANDORABOTS * EMAIL </pattern>
<template><srai>UNSUBSCRIBE PANDORABOTS EMAIL</srai></template></category>
<category><pattern>_ UNSUBSCRIBE * PANDORABOTS EMAIL *</pattern>
<template><srai>UNSUBSCRIBE PANDORABOTS EMAIL</srai></template></category>
<category><pattern>_ UNSUBSCRIBE * PANDORABOTS EMAIL </pattern>
<template><srai>UNSUBSCRIBE PANDORABOTS EMAIL</srai></template></category>
<category><pattern>_ UNSUBSCRIBE PANDORABOTS * EMAIL *</pattern>
<template><srai>UNSUBSCRIBE PANDORABOTS EMAIL</srai></template></category>
<category><pattern>_ UNSUBSCRIBE PANDORABOTS * EMAIL </pattern>
<template><srai>UNSUBSCRIBE PANDORABOTS EMAIL</srai></template></category>
<category><pattern>_ UNSUBSCRIBE PANDORABOTS EMAIL *</pattern>
<template><srai>UNSUBSCRIBE PANDORABOTS EMAIL</srai></template></category>
<category><pattern>_ UNSUBSCRIBE PANDORABOTS EMAIL </pattern>

...

<category><pattern> EMAIL * PANDORABOTS * UNSUBSCRIBE *</pattern>
<template><srai>UNSUBSCRIBE PANDORABOTS EMAIL</srai></template></category>
<category><pattern> EMAIL * PANDORABOTS * UNSUBSCRIBE </pattern>
<template><srai>UNSUBSCRIBE PANDORABOTS EMAIL</srai></template></category>
<category><pattern> EMAIL * PANDORABOTS UNSUBSCRIBE *</pattern>
<template><srai>UNSUBSCRIBE PANDORABOTS EMAIL</srai></template></category>
<category><pattern> EMAIL * PANDORABOTS UNSUBSCRIBE </pattern>
<template><srai>UNSUBSCRIBE PANDORABOTS EMAIL</srai></template></category>
<category><pattern> EMAIL PANDORABOTS * UNSUBSCRIBE *</pattern>
<template><srai>UNSUBSCRIBE PANDORABOTS EMAIL</srai></template></category>
<category><pattern> EMAIL PANDORABOTS * UNSUBSCRIBE </pattern>
<template><srai>UNSUBSCRIBE PANDORABOTS EMAIL</srai></template></category>
<category><pattern> EMAIL PANDORABOTS UNSUBSCRIBE *</pattern>
<template><srai>UNSUBSCRIBE PANDORABOTS EMAIL</srai></template></category>
<category><pattern> EMAIL PANDORABOTS UNSUBSCRIBE </pattern>
<template><srai>UNSUBSCRIBE PANDORABOTS EMAIL</srai></template></category>
</aiml>

Using this set of symbolic reductions, the bot will answer the same thing to a variety of inputs such as:
"How can I unsubscribe to Pandorabots email?"
"I am getting email from Pandorabots and I want to unsubscribe."
"Unsubscribe me from Pandorabots email."

For three keywords X, Y and Z, the 95 combinations come from 6 different possible orderings of the keywords (X Y Z, X Z Y, Y X Z, Y Z X, Z X Y, Z Y X ) times 16 different possible insertions of wildcards (from X Y Z to _ X * Y * Z), minus one because we use X Y Z itself as the pattern for the base category.

Second Life Pandora Updates

2007-11-28T09:29:00.000-08:00

Thanks to some members of the Pandorabots community, we have some news about Pandorabots in Second Life.

Destiny Niles found these Pandorabots in SL:

http://www.sparticarroll.com/Pandora+Chatbot.ashx
http://artfossett.blogspot.com/2007/07/pandorabot-npc.html
http://slurl.com/secondlife/Eduserv%20Island/140/127/26
http://slurl.com/secondlife/Buena%20Vista/146/191/28

Marcus L. Endicott revised our earlier Second Life Round-Up

He said he could not find any Metaversetech or Navillus Batra products at what appears to be now http://shop.onrez.com/, and http://www.metaversetech.com/ seems to have
gone underground.

A search of shop.onrez.com for "pandorabots" did reveal three further resources:

Pandorabot Client Kit v1.4.0:

http://shop.onrez.com/item/322201

shop.onrez.com: (CGe) ChatBOT:

http://shop.onrez.com/item/200770

shop.onrez.com: Eliza Doolittle Chatbot:

http://shop.onrez.com/item/421462

Marcus is trying to keep an informal resource list at:

http://www.mendicott.com/secondlife/slbots.asp

You can often find Second Life bots on the Pandorabots Most Popular
list. Try asking the bots, "Where are you?" to see if you get a response
indicating that they are in Second Life.

$3000 Prize for Loebner 2008

2007-11-28T09:16:00.000-08:00

The Loebner Prize cash award for winning the annual bronze medal in 2008 will be $3000, with no "consolation" awards of $250.

Prize sponsor Hugh Loebner said he
added the $250 awards to defray travel costs when he added the
requirement that finalists be present at the competition.
Finalists will NOT have to present for the
2008 competition, so he added the money to sweeten the pot.

Another concern, Loebner said, was the plunge of the U.S. dollar.

Pandorabots bug fix

2007-11-23T10:43:00.000-08:00

Pandorabots fixed a long standing bug in their system. Log in to Pandorabots and select one of your bots. For example, if you have a bot named ALICE, choose ALICE from the list of My Pandorabots. Then navigate to the AIML section. You now see a web page called ALICE >> AIML files. Pandorabots organizes the AIML files in a table. The second column is called Categories. Previously, the data in the Categories column was all zero. The bug fixed, Pandorabots now correctly displays the number of AIML categories in each file.

Loebner Prize 2008 Announcement

2007-11-20T15:41:00.000-08:00

Dr. Hugh Loebner and Professor Kevin Warwick have announced that the 18th annual Loebner Prize Competition, Loebner Prize 2008, will be held on Oct. 12, 2008 at the University of Reading, Reading, UK.

Professor Warwick will be directing the contest, and all questions regarding the contest, including rules, communications protocols, and judging procedures should be directed to
Professor Warwick at kevin@loebnerprize.org

Kevin Warwick is Professor of Cybernetics at the University of Reading, UK, http://www.kevinwarwick.com/.

AIML and the Semantic Web

2007-11-13T15:05:00.000-08:00

Several people have asked about the relationship between OWL, RDF and AIML.
We came across this paper by Eric Freese, Enhancing AIML Bots using Semantic Web Technologies,
http://www.idealliance.org/papers/extreme/proceedings/html/2007/Freese01/EML2007Freese01.html
The relevant idea being you do your OWL-DL logic in RDF and then convert the resulting RDF Graph to AIML when you're done. From the abstract:

This paper discusses a methodology and provides examples of the conversion of RDF triples to AIML topics and categories which can then be used within an AIML-based bot. The statements representing the domain knowledge can then be used in a conversation handled by the responder. The combination of these two technologies allows the knowledge represented within the RDF to be accessed interactively using natural language by a human user.

Gir new #1 Pandorabot

2007-10-29T18:18:00.000-07:00

Perl programmer Chris Prather created Gir, a new Pandorabot based on the free AAA AIML Set, and put it on a couple of IRC channels. The Gir brain, which combines the AAA set with Chris' own custom AIML, provides natural language responses for two of Chris' bots, Bender and Pip. Due to intense IRC traffic, the Gir bot reached the #1 spot on the Pandorabots Most Popular list.

Chris Prather's long-term project is a bot named Bender.
Chris developed his own Net::AIML package for Perl http://search.cpan.org/perldoc?Net::AIML, which makes a connection to Pandorabots. In one incarnation Gir provides fallback conversational abilities for Bender. Gir is also the brains behind his more recent bot Pip, which uses Net::AIML and Acme::LOLCAT, http://search.cpan.org/perldoc?Acme::LOLCAT. LOLCAT transforms English sentences into amusing, idiosyncratic, bad English. For more information on LOLCAT see Wikipedia http://en.wikipedia.org/wiki/Lolcat.

Bender and Pip sit on about a dozen channels on three IRC networks (#swhack on freenode, several channels on irc.perl.org, and two channels on a private IRC server). The IRC traffic through Net::AIML is driving Gir to the #1 spot on Pandorabots.

Chris says, "Piping the AIML response through LOLCAT made for a more believable character as the naive responses that the bot would make were easily attributed to the 'ethos' of the LOLCAT character."

Here Comes Santa Bot

2007-10-26T15:46:00.000-07:00

The A. I. Foundation has created a special Santa Claus bot for the holidays. The Santa bot is based on the Superbot and has a totally unique, new personality tailored to old Saint Nick. The bot brain has no overlap with the A.L.I.C.E. bot. Santa is totally kid-safe and fun for the whole family. For now Santa is free. Tell Santa what you want for Christmas. Have a chat with Santa at http://alicebot.org/Santa/.

Our Santa bot uses an Oddcast/Sitepal avatar with text-to-speech.

Santa bot is still learning. The more you chat with him, the smarter he will become.

Plans for Loebner Prize 2008

2007-10-25T09:54:00.000-07:00

Hugh Loebner has announced that the Loebner Prize 2008 will almost certainly be held at University of Reading, Reading, England on Oct 12. in conjunction with a computer conference to be held there at the same time. The announcement is still unofficial because he does not speak for U of Reading. Professor Kevin Warwick is working with Huma Shah on this, and Loebner says he will be making an announcement soon.

There are a few details which have yet to be decided. Loebner has asked for public comment.

1. Must the contestants be on site during the contest?

2. Dates for applications, selection, etc. If the contestants do not need to be on site, then it is possible that the selection process for the finals can be part of the conference, perhaps the day before the contest.

3. Whether the Loebner Prize Protocol used in the 2006 and 2007 contests will be required in 2008.

The official announcement for the 2008 competition with rules, will be made no later than Nov 15, 2007.

Robot-Nurse

2007-10-23T17:19:00.000-07:00

Human nurses can have peace of mind. Their jobs are secure, but Santa's little helper has come to the rescue to do most of the boring nursing tasks for them.
Robot-Nurse helps nurses in hospitals. Her body is developed by Samsung and her brain by Robot-Hosting.com. The Nursing school and the psychology departments of the University of Auckland are creating her nurse knowledge base. She has (camera) face recognition, (microphone) voice recognition, arms and hands. She talks (speaker) with the Patients, Doctors and Nurses in 8 human languages.

Her brain will be centrally controlled by several global server clusters. She will guard the wards at night and attend the patients; therefore human nurses can sleep with peace of mind. She can do logical reasoning and delivers doctor's prescribed drugs for patients and remind them about their daily exercise routine.

She also stands there and pushes them (verbally) to do their exercise and acts as a couch and builds their enthusiasm.

Version one can not change the bedpans, she is too small for that task, but a few years later (next version) she will be able to do more physical activities, but actually the present version does not have biological growth mechanisms like us.

Another one of her responsibilities is talking with those patients who do not have any visitor to keep their company, tell them some jokes or just carry the conversation to make them happy. Therefore they will not feel lonely. Decades of efforts and work of Dr. Wallace and all scientists and programmers who contributed to the Alice project is used in her natural language processing unit, among many other developed algorithms and sub-systems. For more information, visit Robot-Hosting.com.

UltraHal wins 2007 Loebner Prize

2007-10-21T09:21:00.001-07:00

Hugh Loebner announced the results of the 2007 competition today. He said transcripts are not yet available, but he will post them eventually.

Winner - Robert Medeksza
2nd Noah Duncan
3rd Rollo Carpenter

Congratulations to Robert Medeksza! He certainly deserves it. He's been working on AI bots as long as any of us. For anyone who doesn't know, Robert is the creator of the famous UltraHal bot at http://www.zabaware.com/

We would like to welcome Robert to the pool of Loebner Prize winners.

Update: Vladimir Veselov has posted photos from the events at:
http://www.veselov.net/modules/xcgal/thumbnails.php?album=14

2nd Update: Hugh Loebner has posted the contest transcripts and names of the judges at:
http://loebner.net/Prizef/2007_Contest/loebner-prize-2007.html

Pandorabots served 500,000,000th response

2007-10-14T19:24:00.000-07:00

Pandorabots.com, a free web based AIML chat hosting service launched in 2002, served its 500,000,000th (half a billionth) response in October. The
service has 106,000 botmasters signed up and 129,000 bots defined. There have also been some recent hardware and software upgrades to Pandorabots that have increased the performace significantly, making it one of the easiest to use sites for chat bot customization.

Alicebot.org server down

2007-10-13T16:45:00.000-07:00

Due to a schedule electric power maintenance in our building, the server hosting Alicebot.org is shut down today, Saturday October 13, and tomorrow, Sunday October 14. The time zone is US/Pacific. Alicebot.org should be back up and running Monday morning.

New Blog

2007-10-06T15:41:00.000-07:00

I created a long-overdue blog version of the ALICE A. I. Foundation News. I am just getting started with blogging and welcome your suggestions and feedback. The Alicebot blog is an aggregator of news stories, press releases, and announcements related to ALICE and AIML free software technology. You can check it out at alicebot.blogsot.com.

New Release of Charlix Desktop Assistant

2007-10-06T15:39:00.001-07:00

Charles Chevallier has announced that Charlix is back with a new release. Charlix is a desktop assistant. He is based in AIML from the implementation of Dr. Richard S. Wallace's A.L.I.C.E. system.

Following an old suggestion from Mehri (RebeccaAIML developer http://rebecca-aiml.sourceforge.net/) he added many scripts for new Linux users to install Java, Acrobat reader, torrent clients, plugins for Firefox, file sharing software, USB gamepads, Microsoft fonts, drivers for MP3 and DVD, MIDI capabilities, Skype, and plenty of software for Debian distributions. It can turn DMA on or turn numlock on. It includes warnings on security and legal issues.

He also included math.aiml that KnyteTrypper posted on this list, which he modified for Linux shell commands. Charles gives credit to the late KnyteTrypper because his forum http://knytetrypper.proboards19.com/index.cgi helped him a lot to produce his pandorabot demo.

He also added misspelled.aiml and repetition.aiml based on Wikipedia's list of most common repetitions and mistakes.

Download Charlix free at http://charlix.sourceforge.net/

Version 0.98 of RebeccaAIML released

2007-10-06T15:37:00.000-07:00

Frank Mehri Hassanbad (mehri) has released the latest major version of RebeccaAIML, codenamed Slatter. Version 1.1tp1 was released in August, followed shortly thereafter by 1.1tp2 and 1.1tp3 in September. RebeccaAIML is an enterprise cross platform open source AIML development platform. RebeccaAIML supports C++, Java, C#, and Python as well as many other programming languages and AIML development out of the box. RebeccaAIML also comes with an array of AIML administration tools, great documentation, and an eclipse AIML editor plugin.

Check out the main page: http://rebecca-aiml.sourceforge.net/index.htm
Check out the user guide for plenty of screen shots of this tech release and instructions on upgrading: http://rebecca-aiml.sourceforge.net/userGuide.htm
And finally, download it and give it a try: http://rebecca-aiml.sourceforge.net/download.htm

Some of the new features in the Slatter release include:

A windows installer
An Eclipse plugin for using Eclipse as an AIML editor
Support for a multitude of programming languages such as C++, C#, Java, and Python
Excellent, fully documented, and easy to use APIs for various programming languages
Safe multi-process and multi-thread access to AIML
Scalability. RebeccaAIML can support an infinite number of users, bots, and, end users as long as you have hard drive space for more.
Fast start times.
Better foreign character support.

A. I. Foundation God bot

2007-10-06T15:34:00.000-07:00

The A. I. Foundation has released its own version of the highly successful AIML God bot originally created by Nicolas Roy. The God bot started as a clone of ALICE running on Pandorabots. Nicolas added some very nice Flash animation on the front-end. The God bot is consistently one of the most popular bots on Pandorabots. Intended to be humorous and fun, the God bot is not affiliated with any religion.

Click here to chat with the God bot.

German AIML Update

2007-10-06T15:33:00.000-07:00

Christian Drossmann, the author of German.aiml, has re-emerged on our mailing list and brought us up to date on his life. He says he has been lurking on the Alicebot mailing lists for some time. Christian says that his address drossmann@arcormail.de has fallen into disuse some time ago due to excessive spamming. His requests that we contact him through his website via mail at drossmann dot de.

Furthermore, because he continues receive email about Alice, Christian decided to put up a page again with some info in German. There are a lot of bots out there, including bots for messageboards etc. that are based on the old German.aiml. The new side for German AIML is http://www.drossmann.de/. Christian says, "Maybe there *will* be an updated version...who knows? Sometimes I miss the coding ;-)"

What is the currency of...

2007-10-06T15:29:00.000-07:00

Steve Worswick (Square Bear - http://www.mitsuku.com/) has written an AIML file that will educate your bot in the different currencies of the world. He wants to share it with all AIML botmasters: http://www.square-bear.co.uk/aiml/currency.aiml.

2007 Loebner Prize Contest Has Only 3 Entries

2007-09-27T20:05:00.001-07:00

Hugh Loebner announced that the finalists for Loebner Prize 2007 are:

(a) Rollo Carpenter - (Icogno Ltd.)
(b) George Medeksza - (Zabaware)
(c) Noah Duncan. (self)

There were no other entries this year, in the annual contest billed as the first real-world Turing Test. Due to technical issues ALICE, the contest winner in 2000, 2001 and 2004, was not entered in this years' competition. It seems that many others stayed away as well. The contest will be held on October 21 at Loebner's apartment in New York City.

Progam Q 1.0 embeds Charlix

2006-04-21T18:56:00.000-07:00

Houssem BDIOUI is glad to announce the release of version 1.0 of Program Q (QAIML):
http://sourceforge.net/projects/qaiml

This release is including the Charlix project (http://sourceforge.net/projects/charlix).It's a very advanced aiml set offering several features. One of those is the 'Bad Answer' feature. Please refer to its Disclaimer (in http://charlix.sourceforge.net/)

Here are the main new changes:
+ Embedded Charlix project (thanks to Charles chevalier)
+ New tags support (more compliant with AIML 1.0.1)
+ Added support for the system tag (Works only on *nix systems for the moment)
+ Implemented the input tag (with its index)
+ Support for the learn tag (still experimental but seems to work!)
+ Support for uppercase
+ bot.vars text file is migrated into bot.xml xml file
+ New vars.xml file:
+ loaded at startup
+ Saved back when the AIMLParser class is destroyed (backup file saved as well)
+ Log file:
* Message error when an aiml file has not been correctly parsed
* Highlight warnings when an unknown tag has been parsed
* Contains system execution trace
+ Copied popup script file along with the QAIML binary (linux distribution - charlix specific)
+ Added new English contractions ('s,'m, ...) substitutions in the substitutions.xml file
+ template-side 'that' tag was not supporting the index attribute
+ Limiting the that & input lists to 50 items (to avoid overflow)
+ srai & sr tags were modifying the input & that lists
+ Fixed spaces strategy when parsing xml: A space is automatically added between 2 sibling non-text xml elements
+ Graph master updated to allow "overwriting" of new categories + All the characters are now accepted as the user input

Houssem awaits your feedback which were always driving him to enhance this application.
houssem.bdioui (at ) st.com houssem.bdioui (at ) gmail.com