Information AboutChatterbot |
| CATEGORIES ABOUT CHATTERBOT | |
| artificial intelligence applications | |
| chatterbots | |
| instant messaging | |
|
METHOD OF OPERATION A good understanding of a conversation is required to carry on a meaningful dialog but most chatterbots do not attempt this. Instead they "converse" by recognizing cue words or phrases from the human user, which allows them to use pre-prepared or pre-calculated responses which can move the conversation on in an apparently meaningful way without requiring them to know what they are talking about. For example, if a human types, "I am feeling very worried lately," the chatterbot may be programmed to recognize the phrase "I am" and respond by replacing it with "Why are you" plus a question mark at the end, giving the answer, "Why are you feeling very worried lately?" A similar approach using keywords would be for the program to answer any comment including ''(Name of celebrity)'' with "I think they're great, don't you?" Humans, especially those unfamiliar with chatterbots, sometimes find the resulting conversations engaging. Critics of chatterbots call this engagement the ELIZA Effect . Some programs classified as chatterbots use other principles. One example is Jabberwacky , which attempts to model the way humans learn new facts and language. ELLA attempts to use Natural Language Processing to make more useful responses from a human's input. Some programs that use natural language conversation, such as SHRDLU , are not generally classified as chatterbots because they link their speech ability to knowledge of a simulated world. This type of link requires a more complex Artificial Intelligence (eg., a "vision" system) than standard chatterbots have. EARLY CHATTERBOTS The classic early chatterbots are ELIZA and PARRY . More recent programs are Racter , Verbots , A.L.I.C.E. , and ELLA . The growth of chatterbots as a research field has created an expansion in their purposes. While ELIZA and PARRY were used exclusively to simulate typed conversation, Racter was used to "write" a story called ''The Policeman's Beard is Half Constructed''. ELLA includes a collection of games and functional features to further extend the potential of chatterbots. The term "ChatterBot" was coined by Michael Mauldin (Creator of the first Verbot , Julia) in 1994 to describe these conversational programs in a conference paper written for the Twelfth National Conference on Artificial Intelligence . MALICIOUS CHATTERBOTS Malicious chatterbots are frequently used to fill chat rooms with spam and advertising, or to entice people into revealing personal information, such as bank account numbers. They are commonly found on Yahoo! Messenger , .NET Messenger Service , AOL Instant Messenger and other Instant Messaging protocols. CHATTERBOTS IN MODERN AI Most modern AI research focuses on practical engineering tasks. This is known as Weak AI and is distinguished from Strong AI , which would require Sapience and reasoning abilities. Chatterbots have proved of some practical use in Information Retrieval and Online Help systems. But much of the interest in them derives from their relevance to questions about strong AI, and in particular the Turing Test . Chatterbot technology does bear some resemblance to aspects of Natural Language research in AI, though it is debatable how much of a contribution they offer, since 'humanlike' conversational abilities are most easily simulated by imitating disjointed chit-chat rather than attempting logical dialogue. For example, one of the 'most-human' natural language chatterbots, A.L.I.C.E. , achieves its effect from a huge database of patterns and responses, encoded in a markup language called AIML ('Artificial Intelligence Markup Language'). If the input sentence matches a specified pattern, then the corresponding response is generated (possibly with substitution of sub-patterns), and this is essentially the same technique that ELIZA , the first chatterbot, was using back in 1966 . Another well-known program, known as Jabberwacky , may seem closer to being genuinely 'intelligent', as it is claimed to learn new responses based on user interactions, rather than being driven from a static database like most other exisiting chatterbots. But even here the conversational results are very poor whenever any temporal coherence is required to keep track of what is going on. Genuine reasoning, rather than mere pattern-matching response to the user's last input, requires far more sophisticated information processing. Some within the chatterbot community aim to rebut these sorts of objections by asking, "How do we know that humans don't also just follow some cleverly devised chatterbot-style rules?" But even a casual human conversation about what to wear or football teams typically involves a coherent train of mutual responses, and no chatterbot based on the usual pattern-matching-response mechanism comes close to being convincing for more than a few sentences if any attempt is made to engage in such a coherent and purposeful conversation. Although chatterbots have these serious limitations, there is some continuity between the processes they use and those employed in AI programs and this can give them a potential role in AI education. SEE ALSO EXTERNAL LINKS
|
|
|