Chatterbot

A chatbot (or chatterbot) is a type of conversational agent, a computer program designed to simulate an intelligent conversation with one or more human users via auditory or textual methods. Such computer programs can also be referred to as "Artificial Conversational Entities" within some specific contexts. Although many chatbots appear to intelligently interpret human input prior to providing a response, 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. Chatbots may also be referred to as talk bots, chat bots, or chatterboxes.

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

Method of operation

Usually a good contextual understanding of a conversation is required to carry out a meaningful dialog, however, 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 without necessarily requiring the chatbot to actually understand or comprehend what is being said. Much debate has taken place regarding what it may mean to "actually understand". Some claim that the term "to actually understand" is inherently meaningless, because the only available criterion to demonstrate apparent "understanding" is the ability to produce valid responses which superficially indicate an understanding of the conversation being held. The famous Chinese Room argument presented by British philosopher John Searle, maintains that machines in principle may not necessarily require any "understanding" whatsoever to produce meaningful responses.^[2] Another famous example of this line of argument against the rationale of the Turing test is Ned Block's Blockhead argument. Nevertheless, some chatbots can be quite convincing in their ability to cause users, especially those unfamiliar with the technology, to find the resulting conversations engaging.

Some programs classified as chatterbots are based upon different principles. One notable example is Jabberwacky, which attempts to model the way humans learn new language based on user interactions. Others aim to use natural language processing to produce more meaningful responses from an apparent attempted level of understanding of user input.

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. and Jabberwacky.

The growth of chatterbots as a field of research has created an expansion in their range of purposes and potential applications. While ELIZA and PARRY were used exclusively to simulate typed conversation, many 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, and this is distinguished from strong AI, which would require sapience and logical reasoning abilities. This is the same technique ELIZA, the first chatterbot, was using back in 1966.

Another notable program, known as Jabberwacky, learns new responses and context based on real-time user interactions, rather than being driven from a static database like many other existing chatterbots. 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.^{[citation needed]} Although such programs show initial promise, many of the existing results in trying to tackle the problem of natural language still appear fairly poor, and it seems reasonable to state that there is currently no general purpose conversational artificial intelligence. This has led some software developers to focus more on the practical aspect of chatterbot technology - information retrieval.

A common rebuttal often used within the AI community against criticism of such approaches asks, "How do we know that humans don't also just follow some cleverly devised rules?" (in the way that Chatterbots do). Two famous examples of this line of argument against the rationale for the basis of the Turing test are John Searle's Chinese room argument and Ned Block's Blockhead argument.

Virtual assistants in commercial environments

Automated conversational systems have now progressed from the original designs and applications of the first widely used chatterbots. Currently several large commercial entities such as Lloyds Banking Group, Royal Bank of Scotland, Renault and Citroën are already utilizing virtual assistants to reduce expenditures on call centres and provide a first point of contact that can inform the user exactly of points of interest, provide support, capture data from the user and promote products for sale.

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

Many organizations try to encourage and support developers all over the world to develop chatterbots that able to do variety of tasks, such as passing the Turing test and 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 
• 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