------------------------------------http://en.wikipedia.

org/wiki/List_of_artificial_intelligence_projects -----Main

AIML Overview
By Dr. Richard S. Wallace AIML, or Artificial Intelligence Mark-up Language enables people to input knowledge into chat-bots based on the A.L.I.C.E free software technology. AIML was developed by the Alicebot free software community and I during 19952000. It was originally adapted from a non-XML grammar also called AIML, and formed the basis for the first Alicebot, A.L.I.C.E., the Artificial Linguistic Internet Computer Entity. AIML, describes a class of data objects called AIML objects and partially describes the behavior of computer programs that process them. AIML objects are made up of units called topics and categories, which contain either parsed or unparsed data.
Parsed data is made up of characters, some of which form character data, and some of which form AIML elements. AIML elements encapsulate the stimulus-response knowledge contained in the document. Character data within these elements is sometimes parsed by an AIML interpreter, and sometimes left unparsed for later processing by a Responder.

CATEGORIES
The basic unit of knowledge in AIML is called a category. Each category consists of an input question,an output answer, and an optional context. The question, or stimulus, is called the pattern. Theanswer, or response, is called the template. The two types of optional context are called "that" and"topic." The AIML pattern language is simple, consisting only of words, spaces, and the wildcard symbols _ and *. The words may consist of letters and numerals, but no other characters. The pattern language is case invariant. Words are separated by a single space, and the wildcard characters function like words. The first versions of AIML allowed only one wild card character per pattern. The AIML 1.01 standard permits multiple wildcards in each pattern, but the language is designed to be as simple as possible for the task at hand, simpler even than regular expressions. The template is the AIML respons or reply. In its simplest form, the template consists of only plain, unmarked text. More generally, AIML tags transform the reply into a mini computer program which can save data, activate other programs, give conditional responses, and recursively call the pattern matcher to insert the responses from other categories. Most AIML tags in fact belong to this template side sublanguage. AIML currently supports two ways to interface other languages and systems. The <system> tag executes any program accessible as an operating system shell command, and inserts the results in the reply. Similarly, the <javascript> tag allows arbitrary scripting inside the templates. The optional context portion of the category consists of two variants, called <that> and <topic>. The <that> tag appears inside the category, and its pattern must match the robot’s last utterance. Remembering one last utterance is important if the robot asks a question. The <topic> tag appears outside the category, and collects a group of categories together. The topic may be set inside any template.

the portion bound to the wildcard * may be inserted into the reply with the markup <star/>. Any combination of (1)-(6). Though posing some risk to novice programmers.AIML is not exactly the same as a simple database of questions and answers. may be treated as the subsentence "Yes.R. for example we tend to prefer patterns like "WHO IS SOCRATES" to ones like "DO YOU KNOW WHO SOCRATES IS" when storing biographical information about Socrates. (2). Synonyms: Map different ways of saying the same thing to the same reply. Symbolic Reduction: Reduce complex grammatic forms to simpler ones. Usually. Symbolic Reduction Symbolic reduction refers to the process of simplifying complex grammatical forms into simpler ones. Many of the more complex forms reduce to simpler forms using AIML categories designed for symbolic reduction: <category> <pattern>DO YOU KNOW WHO * IS</pattern> <template><srai>WHO IS <star/></srai></template> </category> Whatever input matched this pattern. A sentence beginning with the word "Yes" for example. but also any others recursively reached through <srai>." may mean "stimulus-response. so that the output depends not only on one matched category. (6). Each of these is described in more detail in a subsection below: (1). (3). Detecting keywords anywhere in the input.I." "symbolic reduction." stands for artificial intelligence. The pattern matching "query" language is much simpler than something like SQL. but "S. Divide and Conquer: Split an input into two or more subparts. the atomic patterns in categories storing robot knowledge are stated in the simplest possible terms. (5). we surmised that including <srai> was much simpler than any of the iterative block structured control tags which might have replaced it." The disagreement over the acronym reflects the variety of applications for <srai> in AIML. RECURSION AIML implements recursion with the <srai> operator." or "synonym resolution. (7). The "A. No agreement exists about the meaning of the acronym. and the reply formed by combining the replies to each. Conditionals: Certain forms of branching may be implemented with <srai>. and combine the responses to each." plus whatever follows it. But a category template may contain the recursive <srai> tag. Divide and Conquer Many individual sentences may be reduced to two or more subsentences." "syntactic rewrite." "simple recursion. Spelling or grammar corrections. The danger of <srai> is that it permits the botmaster to create infinite loops. (1). . This category reduces any input of the form "Do you know who X is?" to "Who is X?" (2). if it has more than one word. (4).

Synonyms are perhaps the most common application of <srai>. Spelling and Grammar correction The single most common client spelling mistake is the use of "your" when "you’re" or "you are" is intended." <srai>YOU ARE A <star/></srai> </template> </category> Here the bot both corrects the client input and acts as a language tutor. Not every occurrence of "your" however should be turned into "you’re." A small amount of grammatical context is usually necessary to catch this error: <category> <pattern>YOUR A *</pattern> <template>I think you mean "you’re" or "you are" not "your. Synonyms The AIML 1. Many ways to say the same thing reduce to one category.01 standard does not permit more than one pattern per category. (3). . which contains the reply: <category> <pattern>HELLO</pattern> <template>Hi there!</template> </category> <category> <pattern>HI</pattern> <template><srai>HELLO</srai></template> </category> <category> <pattern>HI THERE</pattern> <template><srai>HELLO</srai></template> </category> <category> <pattern>HOWDY</pattern> <template><srai>HELLO</srai></template> </category> <category> <pattern>HOLA</pattern> <template><srai>HELLO</srai></template> </category> (4).<category> <pattern>YES *</pattern> <template><srai>YES</srai> <sr/></template> </category> The markup <sr/> is simply an abbreviation for <srai><star/></srai>.

" the categories execute a conditional branch depending on whether "he" has been set. The general format of four AIML categories is illustrated by this example borrowed from ELIZA: <category> <pattern>MOTHER</pattern> <template> Tell me more about your family. (6). Consider three categories: <category> <pattern>WHO IS HE</pattern> <template><srai>WHOISHE <get name="he"/></srai></template> </category> <category> <pattern>WHOISHE *</pattern> <template>He is <get name="he"/>.</template> </category> <category> <pattern>WHOISHE UNKNOWN</pattern> <template>I don’t know who he is. Each of the last three categories uses <srai> to link to the first. using only the <srai> tag. </template> </category> <category> <pattern>_ MOTHER</pattern> <template><srai>MOTHER</srai></template> </category> <category> <pattern>MOTHER _</pattern> <template><srai>MOTHER</srai></template> </category> <category> <pattern>_ MOTHER *</pattern> <template><srai>MOTHER</srai></template> </category> The first category both detects the keyword when it appears by itself. The second category detects the keyword as the suffix of a sentence. The third detects it as the prefix of an input sentence.(5). AIML also provides the equivalent function through the <condition> tag.</template> </category> Provided that the predicate "he" is initialized to "Unknown. . but it needs to be written and stored only once. As a convenience to the botmaster. so that all four cases produce the same reply. Keywords Frequently we would like to write an AIML template which is activated by the appearance of a keyword anywhere in the input sentence. and finally the last category detects the keyword as an infix. Conditionals It is possible to write conditional branches in AIML. and provides the generic response.

compared with a hypothetical learning machine capable of learning language like a child. Targeting is a cycle incorporating client. The Targeting cycle produces a progressively more refined bot personality. C: That makes no sense. the AIML targeting approach is more efficient. That is the crux of the learning problem in a nutshell.ancientskulls. human. which might mean only turning on the Learn function while in a restricted sandbox.ancientskulls. The art of AIML writing is most apparent in creating default categories. though it is the free labor of many chatters the web that could help the bot grow wise quickly. Specifically. starting with the most common queries. and botmaster. wherein client inputs that find no complete match among the categories are logged by the bot and delivered as Targets the botmaster. the value of that is set to the last sentence in the sequence. if the robot responds with a multiple sentence paragraph. R: The answer is 3. time to Learn a new Line Alice: How would you answer "Where do I find the webpage with Australopithecus?" User: I would say: "http://www. or if the bot is "open to the public" then the teacher has to edit out all the crappy answers supplied by all that "free" labor. It all comes down to editing. which provide noncommittal replies to a wide range of inputs. bot.html" Alice: Thanks. CONTEXT The keyword "that" in AIML refers to the robot’s previous utterance. Of course this scenario raises many problems. such as how to weed out hackers and other garbage givers. who then creates suitable responses. it is an AIML interface to targeting.TARGETING Bot personalities are created and shaped through a cyclical process of supervised learning called Targeting. The choice of the keyword "that" is motivated by its use in ordinary language: R: Today is yesterday.1412926 approximately.net/australopithecus. Either the botmaster edits good quality replies to begin with. Try asking me again. Or I should say. C: That is cool.net/australopithecus. User: Where do I find the webpage with Australopithecus? Alice: http://www. . Here is a very nice example provided found on the alicebot-general mailing list: User: Where do I find the webpage with Australopithecus? Alice: Where do you want to find it? User: Bad Answer Alice.html This is a very nice example. My personal view is that. This is exactly the same as targeting when the botmaster is the teacher.

The robot must find out what is he saying "yes" to.</template> </category> produce the following dialogue: C: Knock knock.. "Do you like movies?. If the robot asked.In AIML the syntax <that>. "What is your favorite movie?. R: Banana who? C: Knock knock. A common application of <that> is found in yes-no questions: <category> <pattern>YES</pattern> <that>DO YOU LIKE MOVIES</that> <template>What is your favorite movie?</template> </category> This category is activated when the client says YES.</that> encloses a pattern that matches the robot’s previous utterance. R: Banana who? C: Knock knock. One interesting application of <that> are categories that enable the robot to respond to knock-knock jokes." continues the conversation along the same lines. . <get name="name"/>. The categories: <category> <pattern>KNOCK KNOCK</pattern> <template>Who is there?</template> </category> <category> <pattern>*</pattern> <that>WHO IS THERE</that> <template><person/> who?</template> </category> <category> <pattern>*</pattern> <that>* WHO</that> <template>Ha ha very funny." this category matches. R: Who’s there? C: Banana. and the response.. R: Who’s there? C: Banana.

I.sunlitsurf. (Ten is in fact the approximate geometric mean of the number of word choices available at each point in assembling a grammatical and sensible sentence). the program implicitly sets the values of the corresponding THAT or TOPIC pattern to the wildcard *.E.C. these . Still. the number of things people actually do say is surprisingly small. The first part of the path to match is the input. the program may distinguish between them depending on the value of <that>. and so on. To be sure. The number of choices for the second word is only about two. but the overall average is just under two words. "Say you have ten choices for the first word to begin a sentence. More than just elegant pictures of the A. ten choices for the second word (yielding 100 two-word beginnings)..C. ten choices for the third word (yielding a thousand three-word beginnings). the final step is to choose the reply based on the <topic>. If two or more categories have the same <pattern> and <that>. and never use <topic> unless you write two categories with the same <pattern> and <that>.E. Our experiments with A.in his book How the Mind Works wrote. like: INPUT <that> THAT <topic> TOPIC. R: Orange who? C: Orange you glad I didn’t say banana.I.E.L.L. that pattern and topic pattern along a single path.I.C. brain. If more than one category have the same input pattern. about 2000 words covers 95% of all the first words input to A. The average branching factor decreases with each successive word.I.R: Who’s there? C: Orange. R: Ha ha very funny.com/documentation/gallery/). Specifically.L. A little arithmetic shows that the number of sentences of 20 words or less (not an unusual length) is about 1020. Pinker’s calculations are way off. indicate that the number of choices for the "first word" is more than ten." like: <topic name="CARS"> <category> <pattern>*</pattern> <template> <random> <li>What’s your favorite car?</li> <li>What kind of car do you drive?</li> <li>Do you get a lot of parking tickets?</li> <li>My favorite car is one with a driver. brain contents represented by this graph (http://alice. but it is only about two thousand.C. This structure suggests a design rule: never use <that> unless you have written two categories with the same <pattern>.L. Nancy. Steven Pinker. one of the most useful applications for <topic> is to create subject-dependent "pickup lines. Internally the AIML interpreter stores the input pattern.</li> </random> </template> Considering the vast size of the set of things people could say that are grammatically correct or semantically meaningful." Fortunately for chat robot programmers. When the values of <that> or <topic> are not specified.E. there are some first words ("I" and "You" for example) that have many possible second words. We have plotted some beautiful images of the A.

for we have found all of the "big trees" from "A *" to "YOUR *".L. it attracted few contributors until migrating to the platform-independent Java language in 1998.L.L.L. No other theory of natural language processing can better explain or reproduce the results within our territory.E. brain.C.com/pandora/pics/wallaceaimltutorial.E. of course.E.C.L. These trees may become bigger. and AIML in Java was codenamed "Program A". was implemented in 1995 using SETL.I.L. and AIML.I. or cognitive models to explain how to chat within the limits of A.edu/~bacon. Our stimulus-response model is as good a theory as any other for these cases.nyu. but unless language itself changes we won’t find any more big trees (except of course in foreign languages).E.I. Academics are fond of concocting riddles and linguistic paradoxes that supposedly show how difficult the natural language problem is. Although the original A. was available as free software (often misnamed "open source").E. In the years to come we will only advance the frontier further.E. and certainly the simplest.C. a widely unknown language based on set theory and mathematical logic.C.’s 25.C.L.C.L.E. until the very last human critic cannot think of one sentence to "fool" A. "John saw the mountains flying over Zurich" or "Fruit flies like a banana" reveal the ambiguity of language and the limits of an A. came to be here. *********************http://www.I. increasingly in the hinterlands occupied by only the rarest forms of language.pandorabots.I. The work of those seeking to explain natural language in terms of something more complex than stimulus response will take place beyond our frontier.C.C.L.html -------1a Alicebot Technology History This is a summary of all of the major development streams of the Alicebot technology. Expanding the borders even more we will continue to absorb the stragglers outside. You can read some interesting essays about how A. neural nets. A.000 categories.I.C. already knows about them). The first implementation of A. [Visit the SETL home page at http://cs. If there is any room left for "higher" natural language theories.E. You don’t need a complex theory of learning.E. Our territory of language already contains the highest population of sentences that people use.I.L. Program A The first edition of A..spiral images (see more) outline a territory of language that has been effectively "conquered" by A.I.C. in chronological order. The basic outline of the spiral graph may look much the same.I.] Program B . it lies outside the map of the A.I.E.-style approach (though not these particular examples.

Program B. Development Richard Wallace began development of the program in 1995. It is one of the strongest programs of its type and has won the Loebner Prize. AOL Instant Messenger (Vlad Zbarskiy).E. Program D Program B Java edition was based on pre-Java 2 technology. justified granting the next code letter "D" to his latest Alicebot Java edition. opening up a whole class of editors and tools for AIML development. it did not take advantage of newer Java features such as Swing and Collections.L. .WxWindows (Philippe Raxhon).C.E. is a natural language processing chatterbot—a program that engages in a conversation with a human by applying some heuristical pattern matching rules to the human's input.I. Program B was a breakthrough in A. and added many new features. Jon Baer recoded Program B with Java 2 technology. More than 300 developers contributed to A. also referred to as Alicebot. Program C Jacco Bikker created the first C/C++ implementation of AIML in 2000. awarded to accomplished humanoid.C. IRC (Anthony Taylor). The name of the bot was chosen because the computer that ran the first version of the software was called Alice. while at Lehigh University. free software development.I.E.E. *************************************http://www. Beginning in November 2000. However. plus the fact that Jon named his bot "DANY". Program B won the Loebner Prize. 2001 and 2004). and in its online form it also relies on a hidden third person. (Artificial Linguistic Internet Computer Entity).I. the program is unable to pass the Turing test.C. in January 2000. talking robots. AIML transitioned to a fully XML-compliant grammar. and COM (Conan Callen). the C/C++ implementations of the Alicebot engine and AIML. as even the casual user will often expose its mechanistic aspects in short conversations. A. Although the program ran on many different platforms. It was inspired by Joseph Weizenbaum's classical ELIZA program.L.C.html --------1b A. or simply Alice. three times (in 2000. This collection of code has come to be known as "Program C".alicebot. Program D is the only the Java edition of the Alicebot engine actively supported.L. an annual Turing Test. This giant leap in the interface and the core.I.org/history/technology.L. Program B was the first widely adopted free AIML software. This was followed by a number of development threads in C/C++ that brought the Alicebot engine to CGI-scripts.Launched in 1999.

the illusion of a human writer could be instantly dispelled. Using almost no information about human thought or emotion. or could continue through several interchanges. When the "patient" exceeded the very small knowledge base. running the DOCTOR script. It was 15 years before the personal computer became familiar to the general public. Depending upon the initial entries by the user. publishing AIML sets in various human languages. DOCTOR sometimes provided a startlingly human-like interaction. provided a "parody" of "the responses of a [1] nondirectional psychotherapist in an initial psychiatric interview. a simulation of a Rogerian psychotherapist. The current incarnation of the Java implementation is Program D." He chose the context of psychotherapy [2] to "sidestep the problem of giving the program a data base of real-world knowledge". responding to "My head hurts" with "Why do you say your head hurts?" The response to "My mother hates me" would be "Who else in your family hates you?" ELIZA was implemented using simple pattern matching techniques.The program was rewritten in Java beginning in 1998. ****************http://en. the therapeutic situation being one of the few real human situations in which a human being can reply to a statement with a question that indicates very little specific knowledge of the topic under discussion. First implemented in Weizenbaum's own SLIP list-processing language. It was one of the firstchatterbots in existence. Subsequent to Richard Wallace's 2001 publication of an AIML specification. ELIZA worked by simple parsing and substitution of key words into canned phrases. the most famous of which was DOCTOR. In 1966. It was sometimes so convincing that there are many anecdotes about people becoming very emotionally caught up in dealing with DOCTOR for several minutes until the machine's true lack of [citation needed] understanding became apparent. and continuing the spread of the technology as a free/open source venture.wikipedia. interactive computing (via a teletype) was new. For example. it is a context in which the question "Who is your favorite composer?" can be answered acceptably with responses such as "What about your own favorite composer?" or "Does that question interest you?" ELIZA was named after Eliza Doolittle. and three decades before most people encountered attempts . numerous other developers have taken up where Wallace left off. even after Weizenbaum explained to them how it worked. Overview Weizenbaum said that ELIZA. but was taken seriously by several of its users. DOCTOR might provide a generic response. a working-class character in George Bernard [3] Shaw's play Pygmalion. ELIZA was written at MIT by Joseph Weizenbaum between 1964 and 1966. for example. The program uses an XML Schema called AIML (Artificial Intelligence Markup Language) for specifying the heuristic conversation rules.org/wiki/Artificial_Linguistic_Internet_Computer_Entity --------2a ELIZA is a computer program and an early example of primitive natural language processing. implementing free and open sourceAIML interpreters in a variety of programming languages. ELIZA operated by processing users' responses to scripts. who is taught to speak with an upper-class accent.

Response and legacy Lay responses to ELIZA were disturbing to Weizenbaum and motivated him to write his book Computer Power and Human Reason: From Judgment to Calculation. The 1980 game The Prisoner incorporated ELIZA-style interaction within its gameplay. Other versions adapted ELIZA around a religious theme. desired to explore the use of computers for writing literature. The Israeli poet David Avidan. There are many programs based on ELIZA in different programming languages.at natural language processing in Internet services like Ask. In the 1976 article "Computer Power and Human Reason. in 1980. In the foreword he [5] presented it as a form of constrained writing. written in 1975). Weizenbaum notes how quickly and deeply people became emotionally involved with the computer program. In the independent documentary film Plug & Pray (2010) Weizenbaum said that only people who misunderstood ELIZA called it a [4] sensation. taking offence when he asked to view the transcripts. such as ones featuring Jesus (both serious and comedic) and another Apple II variant called I Am Buddha. Both these games appeared some nine years after the original ELIZA. written on and for the PLATO system in 1974. Although those programs included years of research and work. After the main character. . a company called "Don't Ask Software".com or PC help systems such as Microsoft Office Clippy. and the second may have been Moria. who is shown interviewing other prominent characters at various points in the game's plot. Atari. she is revealed to be a highly advanced AI." an excerpt of which is included in The New Media Reader edited by Noah Wardrip-Fruin and Nick Montfort. the 1975 game that spawned the interactive fiction genre. Dungeon (1975) (The first was probably "dnd". For example. created a version called "Abuse" for the Apple II. founded by Randy Simon. The 2011 action-RPG Deus Ex: Human Revolution includes among its cast a news media personality named "Eliza Cassan". It is likely that ELIZA was also on the system where Will Crowther created Colossal Cave (Adventure). saying it was an invasion of their privacy. which verbally abused the user based on the user's [6] input. Don Daglow wrote an enhanced version of the program calledEcala on a PDP10 mainframe computer at Pomona College in 1973 before writing what was possibly the second or third computer role-playing game. even asking him to leave the room while they were working with the DOCTOR script. and Commodore PCs. ELIZA remains a milestone simply because it was the first time a programmer had attempted such a human-machine interaction with the goal of creating the illusion (however brief) of human-human interaction. in which he explains the limits of computers. He conducted several conversations with an APL implementation of ELIZA and published them . as he wants to make clear in people's minds his opinion that the anthropomorphic views of computers are just a reduction of the human being and any life form for that matter. Adam Jensen. George Lucas and Walter Murch incorporated an Eliza-like dialogue interface in their screenplay for the feature film THX-1138 in 1969. who was fascinated with future technologies and their relation to art.Eight Authentic Talks with a Computer. Influence on games ELIZA had an impact on a number of early computer games by demonstrating additional kinds of interface designs. hunts her down.in English. and in his own translation to Hebrew under the title My Electronic Psychiatrist .

and usage in the fields of sales and marketing is underway. Purpose The stated purpose of the project is to create an artificial intelligence that is capable of passing the Turing Test.cs.el (circa 1985) in Emacs lisp: http://www.com/downloads/fileinfo.php?id=9780#info Written in TDBS for the Kakadu Konnection BBS in Darwin Australia and widely distributed to other TBBS Bulletin Boards in 1989. in the Musée du Berry. Its stated aim is to "simulate natural human chat in an interesting.net/eliza/Eliza.Inhabitants of the underground future world of THX would retreat to "confession booths" when stressed.org/wiki/ELIZA ------3a Jabberwacky is a chatterbot created by British programmer Rollo Carpenter. controlled approach to sit atop the general conversational AI. It is designed to mimic human interaction and to carry out conversations with users. France. Source code in Guile Scheme: https://github.wikipedia. The ultimate intention is that the program move from a text based system to be wholly voice operated— learning directly from sound and other sensory inputs.chayden. one called 'Critic' and the other 'Artist'.com/apgwoz/chatter ----------------------------------------------------------------------------------http://en. The visitor was supposed to help them converse by typing in to 'Artist' what 'Critic' said. two art-oriented ELIZA-style programs written in BASIC.tcl. and based very closely on Weizenbaum's published description of the program: http://www.tk/9235 Source code in BASIC: http://www. Bourges. running on two separate Amiga 1000 computers.edu/afs/cs/project/airepository/ai/areas/classics/eliza/emacs/0. The secret was that the two programs were identical. aiming to bring together the best of both approaches. Recent developments do allow a more scripted.org Trans-Tex Software has released shareware versions for Classic Mac OS and Mac OS X: Trans-Tex Software doctor. Unlike more traditional AI programs. Its creator believes that it can be incorporated into .wowinterface.php?page=22 Used in AGT: Automatic Goblin Therapist (World of Warcraft addon) http://www.atariarchives. and initiate a one-sided Eliza-formula conversation with a Jesus-faced computer who claimed to be "Omm". Source code in Tcl: http://wiki. It is an early attempt at creating an artificial intelligence through human interaction. the learning technology is intended as a form of entertainment rather than being used for computer support systems or corporate representation. In 1988 the British artist and friend of Weizenbaum Brian Reffin Smith created and showed at the exhibition 'Salamandre'.html Using Z80 assembly language on the TI-83 Plus: ticalc. entertaining and humorous manner".html.org/bigcomputergames/showpage. It is not designed to carry out any other functions. and vice versa.cmu. Implementations          Using Java.

wins the Loebner Prize October 2008 – A new variant of Jabberwacky is launched.E September 2005 – George.L. drivers update.. burn cds.org/chatbot/kar_intelligent_computer1/------6a PARRY was an early example of a chatterbot..chatbots.wikipedia. We can sort all these functions in 4 categories : Family Education Professionnal Disability --------------------------------------http://www. Timeline         1981 – The first incarnation of this project is created as a program hard-coded on a Sinclair ZX81. Cleverbot Cleverbot is an alternative bot to Jabberwacky. It was beaten by computer chat program A. English. intending both to be useful and entertaining. It was beaten by Juergen Pirner's Jabberwock (A German based chat program) September 2004 – Jabberwacky is awarded second place in the Loebner Prize. It is a human machine interface based on artificial intelligence for disability based on head movements.objects around the home such as robots or talking pets. 2.I. German and Spanish! It has more than 630 functions (webbrowser. text-to-speech.org/wiki/Jabberwacky -------4a KAR Intelligent Computer© (Katia Automatique Robot Intelligent Computer©) is a software with 2 main functions: 1. a character within Jabberwacky. automatical execution. keeping people company. under the name Cleverbot -----------------------------------------------------------------------http://en. home automation. writer. It enables companies to drastically reduce their energy bill and carbon footprint of their information technology infrastructure (. 1988 – Learning AI project founded as 'Thoughts' 1997 – Launched on the Internet as 'Jabberwacky' October 2003 – Jabberwacky is awarded third place in the Loebner Prize. implemented in 1972 by psychiatrist Kenneth Colby.C. another Jabberwacky character.48 %).) All these solutions are combined into a single interface. . more fuzzy and with deeper context. magnifying glass. wins the Loebner Prize September 2006 – Joan. also created by Rollo Carpenter. voice recognition… It can also answer more than 450 000 questions in French.

Functionality SHRDLU was primarily a language parser that allowed user interaction using English terms. and the program was fairly adept at figuring out what the user meant. the arrangement of the alpha keys on a Linotype machine. The user instructed SHRDLU to move various objects around in a the "blocks world" containing various basic objects: blocks. What made SHRDLU unique was the combination of four simple ideas that added up to make the simulation of "understanding" far more convincing. The two groups were then [3] asked to identify which of the "patients" were human and which were computer programs. arranged in descending order of usage frequency in English. One could ask SHRDLU to "put the green cone on the red block" and then "take the cone off". essentially a virtual box filled with different blocks. One was that SHRDLU's world was so simple that the entire set of objects and locations could be described by including as few as perhaps 50 words: nouns like "block" and "cone". PARRY attempted to simulate [1] a paranoid schizophrenic. moving objects. verbs like "place on" and "move to".History PARRY was written in 1972 by psychiatrist Kenneth Colby. Later additions were made at the computer graphics labs at the University of Utah. PARRY and ELIZA (also known as "the Doctor" ) "met" several times. reject. "the cone" would be taken to mean the green cone one had just talked about. naming collections and querying the state of a simplified "blocks world". the user carries on a conversation with the computer. and adjectives like "big" and "blue". While ELIZA was a tongue-in-cheek simulation of a Rogerian therapist. cones.wikipedia. The possible combinations of these basic language building blocks were quite simple. A group of experienced psychiatrists analysed a combination of real patients and computers running PARRY through teleprinters. then at Stanford University. SHRDLU also included a basic memory to supply context. conceptualizations. Another group of 33 psychiatrists were shown transcripts of the conversations. SHRDLU was written in the Micro Planner and Lisp programming language on the DEC PDP-6 computer and a DEC graphicsterminal. [5][6] [1]RFC 439[5] [1] --------------------------------------------------------------------------------http://en. adding a full 3D rendering of SHRDLU's "world". and as such was a much more [2] serious and advanced program than ELIZA. The name SHRDLU was derived from ETAOIN SHRDLU. and beliefs (judgements about conceptualizations: accept. In it. SHRDLU could search back further through the interactions to find the proper . The psychiatrists were able to make the correct identification only 48 percent of the time — a figure consistent [4] with random guessing. PARRY was tested in the early 1970s using a variation of the Turing Test. balls. neutral). The program implemented a crude model of the behavior of a paranoid schizophrenic based on concepts.org/wiki/PARRY -------7a SHRDLU was an early natural language understanding computer program. It was described as "ELIZA with attitude". etc. The most famous of these exchanges occurred at the ICCC 1972. It also embodied a conversational strategy. where PARRY and ELIZA were hooked up [5] over ARPANET and "talked" to each other. developed by Terry Winograd at MIT in 1968-1970.

demographics. Below is a list of some of the things START knows about. directors). It was used by [2] Google's language tools until circa 2007. biographies). Currently. much more. [1] History . SYSTRAN is used by the Dashboard Translation widget in Mac OS X. countries. Linux. SYSTRAN has done extensive work for the United States Department of Defense and the European Commission. lakes. SHRDLU would deduce that blocks could be stacked by looking for examples. You can type your question above or select from the following examples. has been on-line and continuously operating since December. and the original rules SHRDLU was supplied with.wikipedia. ------------------------------------------------------------------------------http://en. Peter Toma in 1968.g. maps. Commercial versions of SYSTRAN can run on Microsoft Windows (including Windows Mobile). and build new ones." instead of merely providing a list of hits..csail. independent of the language parser. Finally. birth dates.. SYSTRAN provides the technology for Yahoo! Babel Fish among others. SHRDLU could also remember names given to objects. START aims to supply users with "just the right information. for instance one could ask "did you pick up anything before the cone?" A side effect of this memory. movies (e. or arrangements of them.. search engines). SYSTRAN systems used Rule-based machine translation (RbMT) technology.edu/ -------9a SYSTRAN. SHRDLU could then answer questions about steeples in the blocks world. weather.g.org/wiki/SHRDLU -------8a START. the world's first Web-based question answering system. with example questions.g. people (e. dictionary definitions. founded by Dr. after having tried it. is one of the oldest machine translation companies. the company had 59 employees of whom 26 are computational experts and 15 computational [4] [4] linguists. Unlike information retrieval systems (e. titles. and Solaris. Historically. and much.context in most cases when additional adjectives were supplied. One could also ask questions about the history. For instance. is that the program could answer questions about what was possible in the world and what was not. As of 2008. With the release of SYSTRAN Server 7 in 2010.. cities. ---------------------------------------------------------------------------------------------http://start. the system can answer millions of English questions about places (e. coordinates. 1993.g. The number of employees decreased from 70 in 2006 to 65 in 2007. SYSTRAN implemented a hybrid rule-based/Statistical [3] machine translation (SMT) technology which was the first of its kind in the marketplace. It has been developed by Boris Katz and his associates of the InfoLab Group at the MIT Computer Science and Artificial Intelligence Laboratory.mit. but would realize that triangles couldn't be stacked. For instance one could say "a steeple is a small triangle on top of a tall rectangle". The "world" contained basic physics to make blocks fall over. political and economic systems). actors.

Ohio.I. 8. before [5] seeing a rebound in 2009 with 8. 9.9%. techniques.wikipedia. and is now traded publicly on the French stock exchange.6 million euros. Its company headquarters is in Paris. The company was sold in 1986 to the Gachot family. built especially for A. and 7. During the dot-com boom. 8. The company was established in La Jolla in California to work on translation of Russian to English text for the United States Air Force during the Cold War. was usually adequate for understanding content.With its origin in the Georgetown machine translation effort. and 8.9%.org/wiki/SYSTRAN-----------10a   Kreator. ---------------------------------------------------------------------http://en.8 million euros in 2007. Revenues had been declining in the early 2000s: 10. while its US headquarters is in La Jolla. although only approximate. California. 10. OpenAIR.6 million euros in 2008. a routing and communication protocol based on a publish-subscribe architecture. research. .2 million euros in 2004. the international language industry started a new era. [4] respectively. the most successful of these [citation needed] being WorldLingo. 57. Large numbers of Russian scientific and technical documents were translated using SYSTRAN under the auspices of the USAF Foreign Technology Division (later the National Air and Space Intelligence Center) at Wright-Patterson Air Force Base. based in Paris.9% of its revenues.3 million euros in 2006. [edit]Business situation Most of SYSTRAN's revenue comes from a few customers. an optimization problem solving software by Intelligentics that uses A.I. SYSTRAN was one of the few machine translation systems to survive the major decrease of funding after the ALPAC Report of the mid-1960s. The quality of the translations.1% comes from the 10 main customers and the three largest customers account for 10. and SYSTRAN entered into agreements with a number of translation integrators.1 million [4] euros in 2005.