From Wikipedia, the free encyclopedia

A chatbot (or chatterbot, or chat bot) is a computer program designed to simulate an intelligent conversation with one or more human users via auditory or textual methods. Traditionally, the aim of such simulation has been to fool the user into thinking that the program's output is a human's (the Turing test). Programs used in this way are sometimes referred to as Artificial Conversational Entities, talk bots or chatterboxes. More recently, however, chatbot-like methods have been used for practical purposes such as online help or personalised service, in which case the program is functioning as a type of conversational agent. What distinguishes a chatbot from more sophisticated Natural language processing systems is the simplicity of the algorithms used. Although many chatbots do appear to interpret human input intelligently to respond, many simply scan for keywords within the input and pull a reply with the most matching keywords, or the most similar wording pattern, from a textual database.

The term "ChatterBot" was originally coined by Michael Mauldin (Creator of the first Verbot, Julia) in 1994 to describe these conversational programs.^[1]

Background

Usually a good contextual understanding of a conversation is required to carry out a meaningful dialog, but many chatbots rely on relatively shallow contexts. Some of them converse by recognizing cue words or phrases in the input, which allows them to use pre-prepared or pre-programmed responses which can move the conversation on in an apparently meaningful way. The Chinese Room argument presented by philosopher John Searle maintains that machines in principle may not necessarily require any "understanding" whatsoever to produce meaningful responses.^[2] Also against the rationale of the Turing test is Ned Block's Blockhead argument. Nevertheless, some chatbots can be quite convincing in their ability: users, especially those unfamiliar with the technology, may find the resulting conversations engaging.

Chatterbot development

The classic historic early chatterbots are ELIZA (1966) and PARRY (1972).^[3][4][5][6] More recent notable programs include A.L.I.C.E., Jabberwacky and D.U.D.E (Agence_Nationale_pour_la_Recherche and CNRS 2006). While ELIZA and PARRY were used exclusively to simulate typed conversation, many chatterbots now include functional features such as games and web searching abilities. A program called Racter has also been used to "write" an original story called The Policeman's Beard is Half Constructed.^[7]

One pertinent field of AI research is natural language processing. Usually, weak AI fields employ specialized software or programming languages created specifically for the narrow function required. For example, A.L.I.C.E. utilises a programming language called AIML which is specific to its function as a conversational agent, and has since been adopted by various other developers of, so called, Alicebots. Nevertheless, A.L.I.C.E. is still purely based on pattern matching techniques without any reasoning capabilities, the same technique ELIZA was using back in 1966. This is not strong AI, which would require sapience and logical reasoning abilities.

Jabberwacky learns new responses and context based on real-time user interactions, rather than being driven from a static database. Some more recent chatterbots also combine real-time learning with evolutionary algorithms which optimise their ability to communicate based on each conversation held, with one notable example being Kyle, winner of the 2009 Leodis AI Award. Still, there is currently no general purpose conversational artificial intelligence, and some software developers focus on the practical aspec, information retrieval.

Virtual assistants in commercial environments

Automated conversational systems have now progressed, and large companies such as Lloyds Banking Group, Royal Bank of Scotland, Renault and Citroën are already using them instead of call centres to provide a first point of contact. Chatbots can also be implemented via Twitter, or Windows Live Messenger (see World of Alice).

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, Windows Live Messenger, AOL Instant Messenger and other instant messaging protocols. There has also been a published report of a chatterbot used in a fake personal ad on a dating service's website.^[8]

Chatterbot competitions

Competitions focus on the Turing test or more specific goals. Two such annual contests are the Loebner Prize and The Chatterbox Challenge.

See also

• Turing test
• Loebner prize
• Markov chain
• List of Chatterbots
• Dialog system
• Interactive online characters

Citations

References

• Computer History Museum (2006), "Internet History - 1970's", Exhibits, Computer History Museum, http://www.computerhistory.org/internet_history/internet_history_70s.shtml, retrieved 2008-03-05  
• Güzeldere, Güven; Franchi, Stefano (1995-07-24), dialogues with colorful personalities of early ai, "Constructions of the Mind", Stanford Humanities Review, SEHR (Stanford University) 4 (2), http://www.stanford.edu/group/SHR/4-2/text/dialogues.html, retrieved 2008-03-05  
• Mauldin, Michael (1994), "ChatterBots, TinyMuds, and the Turing Test: Entering the Loebner Prize Competition", Proceedings of the Eleventh National Conference on Artificial Intelligence, AAAI Press, http://www.aaai.org/Library/AAAI/aaai94contents.php, retrieved 2008-03-05   (abstract)
• Network Working Group (1973), "RFC 439, PARRY Encounters the DOCTOR", The Internet Engineering Task Force (Internet Society), http://tools.ietf.org/html/rfc439, retrieved 2008-03-05  
• Sondheim, Alan J (1997), <nettime> Important Documents from the Early Internet (1972), nettime.org, http://www.nettime.org/Lists-Archives/nettime-l-9707/msg00059.html, retrieved 2008-03-05  

External links

• Chatterbots at the Open Directory Project