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 centers to provide a first point of contact. Chatbots can also be implemented via Twitter, or Windows Live Messenger. For example, the Robocoke chatbot for Coca Cola Hungary. This chatbot provides users with information about the brand Coca Cola, but he can also give users party and concert recommendations all over Hungary. These kind of chatbots are often used for marketing purposes.
Popular online portals like eBay and PayPal are also using multi lingual virtual agents to offer online support to their customers. For example, PayPal uses chatterbot Louise to handle queries in English and chatterbot Léa to handle queries in French. Developed by VirtuOz, both agents handle 400,000 conversations in a month.These agents have been functional since September 2008 on PayPal websites.
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.
Competitions for Chatbots focus on the Turing test or more specific goals. Two such annual contests are the Loebner Prize and The Chatterbox Challenge.
Based on http://en.wikipedia.org/wiki/Chatbots licensed under the Creative Commons Attribution-Share-Alike License 3.0
Showing posts with label Introduction. Show all posts
Showing posts with label Introduction. Show all posts
Saturday, December 31, 2011
Chatbots II - History of Chatbots and their development over time.
In 1950, Alan Turing published his famous article "Computing Machinery and Intelligence" which proposed what is now called the Turing test as a criterion of intelligence. This criterion depends on the ability of a computer program to impersonate a human in a real-time written conversation with a human judge, sufficiently well that the judge is unable to distinguish reliably - on the basis of the conversational content alone - between the program and a real human. The notoriety of Turing's proposed test stimulated great interest in Joseph Weizenbaum's program ELIZA, published in 1966, which seemed to be able to fool users into believing that they were conversing with a real human. However Weizenbaum himself did not claim that ELIZA was genuinely intelligent, and the Introduction to his paper presented it more as a debunking exercise:
[In] artificial intelligence ... machines are made to behave in wondrous ways, often sufficient to dazzle even the most experienced observer. But once a particular program is unmasked, once its inner workings are explained ... its magic crumbles away; it stands revealed as a mere collection of procedures ... The observer says to himself "I could have written that". With that thought he moves the program in question from the shelf marked "intelligent", to that reserved for curios ... The object of this paper is to cause just such a re-evaluation of the program about to be "explained". Few programs ever needed it more.
ELIZA's key method of operation (copied by chatbot designers ever since) involves the recognition of cue words or phrases in the input, and the output of corresponding pre-prepared or pre-programmed responses which can move the conversation forward in an apparently meaningful way (e.g. by responding to any input that contains the word 'MOTHER' with 'TELL ME MORE ABOUT YOUR FAMILY'). Thus an illusion of understanding is generated, even though the processing involved has been merely superficial. ELIZA showed that such an illusion is surprisingly easy to generate, because human judges are so ready to give the benefit of the doubt when conversational responses are capable of being interpreted as "intelligent". Thus the key technique here - which characterises a program as a chatbot rather than as a serious natural language processing system - is the production of responses which are sufficiently vague and non-specific that they can be understood as "intelligent" in a wide range of conversational contexts. The emphasis is typically on vagueness and unclarity, rather than any conveying of genuine information.
More recently, however, interface designers have come to appreciate that humans' readiness to interpret computer output as genuinely conversational - even when it is actually based on rather simple pattern-matching - can be exploited for useful purposes. Most people prefer to engage with programs that are human-like, and this gives chatbot-style techniques a potentially useful role in interactive systems that need to elicit information from users, as long as that information is relatively straightforward and falls into predictable categories. Thus, for example, online help systems can usefully employ chatbot techniques to identify the area of help that users require, potentially providing a "friendlier" interface than a more formal search or menu system. This sort of usage holds the prospect of moving chatbot technology from Weizenbaum's "shelf ... reserved for curios" to that marked "genuinely useful computational methods".
The classic historic early chatterbots are ELIZA (1966) and PARRY (1972). 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. In 1984 a book called The Policeman's Beard is Half Constructed was published, allegedly written by the chatbot Racter (though the program as released would not have been capable of doing so).
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 aspect, information retrieval.
Based on http://en.wikipedia.org/wiki/Chatbots licensed under the Creative Commons Attribution-Share-Alike License 3.0
[In] artificial intelligence ... machines are made to behave in wondrous ways, often sufficient to dazzle even the most experienced observer. But once a particular program is unmasked, once its inner workings are explained ... its magic crumbles away; it stands revealed as a mere collection of procedures ... The observer says to himself "I could have written that". With that thought he moves the program in question from the shelf marked "intelligent", to that reserved for curios ... The object of this paper is to cause just such a re-evaluation of the program about to be "explained". Few programs ever needed it more.
ELIZA's key method of operation (copied by chatbot designers ever since) involves the recognition of cue words or phrases in the input, and the output of corresponding pre-prepared or pre-programmed responses which can move the conversation forward in an apparently meaningful way (e.g. by responding to any input that contains the word 'MOTHER' with 'TELL ME MORE ABOUT YOUR FAMILY'). Thus an illusion of understanding is generated, even though the processing involved has been merely superficial. ELIZA showed that such an illusion is surprisingly easy to generate, because human judges are so ready to give the benefit of the doubt when conversational responses are capable of being interpreted as "intelligent". Thus the key technique here - which characterises a program as a chatbot rather than as a serious natural language processing system - is the production of responses which are sufficiently vague and non-specific that they can be understood as "intelligent" in a wide range of conversational contexts. The emphasis is typically on vagueness and unclarity, rather than any conveying of genuine information.
More recently, however, interface designers have come to appreciate that humans' readiness to interpret computer output as genuinely conversational - even when it is actually based on rather simple pattern-matching - can be exploited for useful purposes. Most people prefer to engage with programs that are human-like, and this gives chatbot-style techniques a potentially useful role in interactive systems that need to elicit information from users, as long as that information is relatively straightforward and falls into predictable categories. Thus, for example, online help systems can usefully employ chatbot techniques to identify the area of help that users require, potentially providing a "friendlier" interface than a more formal search or menu system. This sort of usage holds the prospect of moving chatbot technology from Weizenbaum's "shelf ... reserved for curios" to that marked "genuinely useful computational methods".
The classic historic early chatterbots are ELIZA (1966) and PARRY (1972). 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. In 1984 a book called The Policeman's Beard is Half Constructed was published, allegedly written by the chatbot Racter (though the program as released would not have been capable of doing so).
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 aspect, information retrieval.
Based on http://en.wikipedia.org/wiki/Chatbots licensed under the Creative Commons Attribution-Share-Alike License 3.0
Chatbot I - What exactly is a Chatbot?
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 has been produced by a human (the Turing test). Programs playing this role 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, personalised service, or information acquisition, 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 when generating their responses, 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.
Based on http://en.wikipedia.org/wiki/Chatbots licensed under the Creative Commons Attribution-Share-Alike License 3.0
The term "ChatterBot" was originally coined by Michael Mauldin (Creator of the first Verbot, Julia) in 1994 to describe these conversational programs.
Based on http://en.wikipedia.org/wiki/Chatbots licensed under the Creative Commons Attribution-Share-Alike License 3.0
Monday, February 28, 2011
Chatterbot review 4
A chat bot is also well known as chatterbot. A computer program is design in such a way that the program can continue textual or auditory conversation with human. This technology is mainly use to fool the human and make him feel that he is having conversation with human. This is the so called chat bot. But the recent use of chat bot is different, it is more useful. Nowadays, this technology is use for technical help and support.
It is also use for customer service as conversational agents. You may have heard about processing natural language system. But there is difference between this system and chat bot. The algorithm used in chat bot is much simpler compared to the processing natural language system. Many chat bots show their intelligence while responding textual conversation and some of them have almost same response as if human is responding. Scientists are working for artificial intelligence for many years. Michael Mauldin first introduced the term chat bot in 1994. (His creation was called Verbot, Julia.) He created Verbot, Julia.
A famous article about artificial intelligence is “Computing Machinery and Intelligence” written by Alan Turing. He created a test criterion, named as Turing test. Turing Test is use to determine the level of intelligence of computer programs. He had shown that a human judge could not able to find out the computer program alone from a conversation between human and computer program.
You may have heard about ELIZA (capital letter is used to express but there is no elaboration). It was first developed by Joseph Weizenbaum in 1966. Weuzenbaum designed ELIZA to provide "parody of the responses of a non-directional psychotherapist in an initial psychiatric interview" in his words. ELIZA was based on a principle developed by the psychiatrist Carl Rogers’ client centered therapy. ELIZA was actually used as a role of real therapist.
ELIZA (1966) and PARRY (1972) were historical chatter box. A.L.I.C.E, D.U.D.E AND Jabberwacky are the recent popular chat bot. (Simulate type of conversations were in ELIZA and PARRY, where recent programs also have some features like web search, games and other things.)
ELIZA and PARRY were used to simulate conversations while recent chat bot now have features like web search, games and other things. Natural language processing system is mainly connected to artificial intelligence. A.L.I.C.E. was based on simple technique of pattern making. The same technique was used early in case of ELIZA. Logic approval, reasoning ability and sapience are required for strong AI (artificial intelligence). Jabberwacky is quite fast. It has learned context based instructions and new responses.
The latest chat bots was based on real time evolutionary algorithms. These were optimized with ability that can communicate with each of the conversation held. For example Kyle, the winner of leodis al award 2009. Nowadays the research on AI has no general purposes. But practical aspect was focused in software development organizations. Information retrieval is a reason.
There are different uses of chatter bot. As virtual assistant chatter bot is an effective and worthy solution. The bank services, mobile phone operator services also other call center services can be handled by chatter bot. Famous online portal services like PayPal and eBay used virtual agents on multiple purposes. AI chatter bots can provide restless, 100% correct services. Another type of chatter bot is malicious bot. These are used to fill frequently the chat rooms, spam and trash, advertising. Commonly used messenger services are places to find chat bot. You may have known about the chat bot competitions. The two popular chat bot competitions are The Chatter Box Challenge and Leobner prize.
It is also use for customer service as conversational agents. You may have heard about processing natural language system. But there is difference between this system and chat bot. The algorithm used in chat bot is much simpler compared to the processing natural language system. Many chat bots show their intelligence while responding textual conversation and some of them have almost same response as if human is responding. Scientists are working for artificial intelligence for many years. Michael Mauldin first introduced the term chat bot in 1994. (His creation was called Verbot, Julia.) He created Verbot, Julia.
A famous article about artificial intelligence is “Computing Machinery and Intelligence” written by Alan Turing. He created a test criterion, named as Turing test. Turing Test is use to determine the level of intelligence of computer programs. He had shown that a human judge could not able to find out the computer program alone from a conversation between human and computer program.
You may have heard about ELIZA (capital letter is used to express but there is no elaboration). It was first developed by Joseph Weizenbaum in 1966. Weuzenbaum designed ELIZA to provide "parody of the responses of a non-directional psychotherapist in an initial psychiatric interview" in his words. ELIZA was based on a principle developed by the psychiatrist Carl Rogers’ client centered therapy. ELIZA was actually used as a role of real therapist.
ELIZA (1966) and PARRY (1972) were historical chatter box. A.L.I.C.E, D.U.D.E AND Jabberwacky are the recent popular chat bot. (Simulate type of conversations were in ELIZA and PARRY, where recent programs also have some features like web search, games and other things.)
ELIZA and PARRY were used to simulate conversations while recent chat bot now have features like web search, games and other things. Natural language processing system is mainly connected to artificial intelligence. A.L.I.C.E. was based on simple technique of pattern making. The same technique was used early in case of ELIZA. Logic approval, reasoning ability and sapience are required for strong AI (artificial intelligence). Jabberwacky is quite fast. It has learned context based instructions and new responses.
The latest chat bots was based on real time evolutionary algorithms. These were optimized with ability that can communicate with each of the conversation held. For example Kyle, the winner of leodis al award 2009. Nowadays the research on AI has no general purposes. But practical aspect was focused in software development organizations. Information retrieval is a reason.
There are different uses of chatter bot. As virtual assistant chatter bot is an effective and worthy solution. The bank services, mobile phone operator services also other call center services can be handled by chatter bot. Famous online portal services like PayPal and eBay used virtual agents on multiple purposes. AI chatter bots can provide restless, 100% correct services. Another type of chatter bot is malicious bot. These are used to fill frequently the chat rooms, spam and trash, advertising. Commonly used messenger services are places to find chat bot. You may have known about the chat bot competitions. The two popular chat bot competitions are The Chatter Box Challenge and Leobner prize.
Sunday, February 20, 2011
Chat Bots review 3
Chat bots or chatterbots is a computer program that is designed to simulate intelligent conversation. Their main aim is to fool others into the belief that a particular output was produced by a human rather than by a simulated system. They can communicate with one or more humans or with other chatbots by textual or auditory methods and are capable of remembering the conversations. Such programs are sometimes referred to as Artificial Conversational Entities. They have an independent existence and can make conversations with one another and other humans and make memories that can be looked into. They are capable of handling many users usually on a time shared basis.
Most of them work based on pattern matching and/or pattern recognition and differ from other sophisticated natural language processing systems in the simplicity of their algorithms and their ease of implementation. Though these chatbots appear to interpret data and respond intelligently, they merely scan the input and select a reply with the most matching keywords or most similar word pattern from a textual database of response.
These programs satisfy Turing’s criterion of intelligence. According to this, a program is considered to be intelligent only if it is capable of impersonating a human in a conversation with another human such that it is not possible to judge between a program and a real person based on conversational content alone. Turing’s test determines how well a program is capable of appearing as a real person. The key feature that characterizes a program as a chatbot rather than as a natural language processor is its ability to produce sufficiently vague and non-specific replies that are easily misinterpreted as intelligent under a wide area of conversational contexts. The main focus is thus given to produce intelligent output and not in the clarity of the output.
The earliest of the chatbots in existence are ELIZA, PARRY and RACTER. They are basically natural language processing systems capable of conversing in English. ELIZA still serves as a model for other chatbots. It was written at MIT by Joseph Weizenbaum and published in 1966. ELIZA emulates a Rogerian psychotherapist. It was first implemented in Weizenbaum’s own SLIP list processing language. When conversing with ELIZA user types a sentence which is delimited by a period and the double carriage return serves to transfer the control to ELIZA. It has no keywords in its repository to match words from a non-English language, or the ability to detect the language the input is presented in. It operates by recognizing keywords in the input, comparing them with the database and producing the corresponding pre-programmed responses as output. These responses move the conversation forward in a meaningful way.
ELIZA showed that an illusion of conversing with a real person is surprisingly easy to generate, because human judges are so ready to give the benefit of the doubt when conversational responses are capable of being interpreted as "intelligent". ELIZA scripts exist in Welsh and German as well as in English. There are many programs based on ELIZA in different languages.
Nowadays chatbots are being commonly used in many offices as most people prefer to engage with human like programs. And some of them are ALICE, EWA etc. Chatbots are being used in interactive systems to respond to queries that of the user, that can easily be categorized. These programs can provide a friendly interface and are now employed as virtual assistants and provide accurate information. And since the bots can personally remember things about those they chat with, they will recognize someone who returns to your site and greet them by name, and can inquire into things they said on their last visit.
The chatbots can be programmed explicitly to make it perform the functions of our choice. The bots can be put to use in many places. They can put in any website and in mobile devices that support web applications. They can also be used for advertising and trading purposes. These bots can inform, amuse, survey, advertise, redirect, and more.
The chatbots have become very common and now more effort is being spent in developing bots that are smarter. Chatbots will soon be able to speak their responses out loud with a moving mouth that synchronises to what they are saying. They can be used in advanced system that displays advertisements that are relevant to the current topic of conversation. This makes for highly-focused advertising that has a much stronger likelihood of success than other advertisements.
And the more advanced bots that will be able to answer millions of trivia-type questions about science, facts, people, movies, books, and any topic that interests the user are still being developed.
Most of them work based on pattern matching and/or pattern recognition and differ from other sophisticated natural language processing systems in the simplicity of their algorithms and their ease of implementation. Though these chatbots appear to interpret data and respond intelligently, they merely scan the input and select a reply with the most matching keywords or most similar word pattern from a textual database of response.
These programs satisfy Turing’s criterion of intelligence. According to this, a program is considered to be intelligent only if it is capable of impersonating a human in a conversation with another human such that it is not possible to judge between a program and a real person based on conversational content alone. Turing’s test determines how well a program is capable of appearing as a real person. The key feature that characterizes a program as a chatbot rather than as a natural language processor is its ability to produce sufficiently vague and non-specific replies that are easily misinterpreted as intelligent under a wide area of conversational contexts. The main focus is thus given to produce intelligent output and not in the clarity of the output.
The earliest of the chatbots in existence are ELIZA, PARRY and RACTER. They are basically natural language processing systems capable of conversing in English. ELIZA still serves as a model for other chatbots. It was written at MIT by Joseph Weizenbaum and published in 1966. ELIZA emulates a Rogerian psychotherapist. It was first implemented in Weizenbaum’s own SLIP list processing language. When conversing with ELIZA user types a sentence which is delimited by a period and the double carriage return serves to transfer the control to ELIZA. It has no keywords in its repository to match words from a non-English language, or the ability to detect the language the input is presented in. It operates by recognizing keywords in the input, comparing them with the database and producing the corresponding pre-programmed responses as output. These responses move the conversation forward in a meaningful way.
ELIZA showed that an illusion of conversing with a real person is surprisingly easy to generate, because human judges are so ready to give the benefit of the doubt when conversational responses are capable of being interpreted as "intelligent". ELIZA scripts exist in Welsh and German as well as in English. There are many programs based on ELIZA in different languages.
Nowadays chatbots are being commonly used in many offices as most people prefer to engage with human like programs. And some of them are ALICE, EWA etc. Chatbots are being used in interactive systems to respond to queries that of the user, that can easily be categorized. These programs can provide a friendly interface and are now employed as virtual assistants and provide accurate information. And since the bots can personally remember things about those they chat with, they will recognize someone who returns to your site and greet them by name, and can inquire into things they said on their last visit.
The chatbots can be programmed explicitly to make it perform the functions of our choice. The bots can be put to use in many places. They can put in any website and in mobile devices that support web applications. They can also be used for advertising and trading purposes. These bots can inform, amuse, survey, advertise, redirect, and more.
The chatbots have become very common and now more effort is being spent in developing bots that are smarter. Chatbots will soon be able to speak their responses out loud with a moving mouth that synchronises to what they are saying. They can be used in advanced system that displays advertisements that are relevant to the current topic of conversation. This makes for highly-focused advertising that has a much stronger likelihood of success than other advertisements.
And the more advanced bots that will be able to answer millions of trivia-type questions about science, facts, people, movies, books, and any topic that interests the user are still being developed.
Wednesday, February 16, 2011
The Evolution of Chat Bots
If you are an active internet user then chances are that you already have had experience of talking to chat bots. Either by mistake or out of curiosity you came across one of these computer programs which were designed extra for maintaining a real conversation with humans. Such chat bots can be easily found on many entertaining sites, chat rooms, instant messengers. Hundreds of them are there to keep you company for a small talk or answer your questions on some really complicated topics.
However, the results of talking to chat bots are usually disappointing. Some of them are so poorly created that after a minute of a chat your “virtual” conversation partner will stop talking sense or will keep repeating one and the same phrase. There is only a really small number of programs which are able to keep the ball rolling. Their creators talk about artificial intelligence, and probably in the next few years it will be complicated for us to figure out who we talk to – a human or a bot.
History
The first, and probably, the most famous chat bot is ELIZA. The name refers to Bernard Shaw’s Eliza Doolittle from “Pigmalion” who was taught the language of the high society while the plot was unraveling. The program’s author, Joseph Weizenbaum, created in it 1966 after analyzing work peculiarities of psychotherapists. As we all know, some from experience, some from numerous TV shows, shrinks prefer to have the dialogue with patients in the mode of active listening which implies constant repeats and requests to continue talking. ELIZA communicated using the same model. In this case the chat focussed of asking questions instead of giving answers, the rest of the chat contained filler phrases.
The dull conversation got exciting every now and then when the chat bot was asking questions reacting to the key words in the speech of the chat partner. For example, if you said “My father hates me,” the bot would ask “Who else in the family does hate you?” Of course, there was no deep analysis of the words’ meaning. All the words, used by the chat partner were just a set of character data. However, ELIZA chat bot made a great impact on the future of chat, or chatter, bots, showing that it was possible to mess with the human language and to create some imitation.
1972 the psychiatrist Kenneth Colby wrote another program, his answer to ELIZA. His chat bot, PARRY, imitated communication style of a paranoid schizophrenic. A few times ELIZA and PARRY were given a chance to communicate with each other. Since that time making bots “talk” to each other has become one of the favorite time passing of chat bots’ developers.
Some time later, a number of computer games used the ELIZA’s algorithm, but it was way later, already in the 21st century, when perfect environment for chat bots was found. We are talking now about instant messaging. It all started with Kevin Fox’ AOLiza which again used the same algorithm as our dear friend, ELIZA. In a way it was a very successful experience since many IM users were accustomed to random chat partners and excessive use of bastardized language. Senseless answers of the bot did not discourage people and they tried to search for some meaning in them. Fox’ experiment was very important for the future development of similar programs. Nowadays you can find a lot of chat bots in each IM network, some of them were specially created to mention a certain brand in the conversation.
Testing for Humanity
It is supposed that the ideal chat bot should be able to pass Turing Test. There are even yearly competitions for such programs. The most well-known of them is Loebner Prize.
Turing test was mentioned for the first time by (as the name suggests it) Alan Turing in 1950 in his article “Computing Machinery and Intelligence.” The test is designed to testing the computer for having human intelligence. The idea was to see if computer can “think”. The process goes as following. A human judge is talking with two chat partners, one is human, and the other is computer. The task of the judge is to figure out who is who. If he/she can’t give a definite answer, then it means computer passes the test.
Chat Bots of the 21st century
Loebner Prize encourages developments of chat bots. However, till now there are not many chat bots that are close to leading a “human” conversation. There are two favorites as of now Jabberwacky, A.L.I.C.E. (Artificial Linguistic Internet Computer Entity) and D.U.D.E.. They are constantly developing, learning new responses and trying to take advantage of new technologies.
Chat Bots in Business
A great number of companies that have active internet presence use the technology in their best interests. Chat bots are used as virtual assistants that can answer customer’s questions, help the companies to accomplish their marketing purpose, maintain their twitter accounts.
Future of Chat Bots
More and more developers try to get close to grasping the idea of artificial intelligence. For them there is no question whether they succeed or not. The question is when they will be able to create a computer program that will act, think and talk like a human. And what will be the consequences. Till then the developers will make more attempts in improving existing chat bots and creating new ones. How much time it will take them nobody knows. But better watch out, maybe your new best online friend is a bot.
But then again, maybe not.
However, the results of talking to chat bots are usually disappointing. Some of them are so poorly created that after a minute of a chat your “virtual” conversation partner will stop talking sense or will keep repeating one and the same phrase. There is only a really small number of programs which are able to keep the ball rolling. Their creators talk about artificial intelligence, and probably in the next few years it will be complicated for us to figure out who we talk to – a human or a bot.
History
The first, and probably, the most famous chat bot is ELIZA. The name refers to Bernard Shaw’s Eliza Doolittle from “Pigmalion” who was taught the language of the high society while the plot was unraveling. The program’s author, Joseph Weizenbaum, created in it 1966 after analyzing work peculiarities of psychotherapists. As we all know, some from experience, some from numerous TV shows, shrinks prefer to have the dialogue with patients in the mode of active listening which implies constant repeats and requests to continue talking. ELIZA communicated using the same model. In this case the chat focussed of asking questions instead of giving answers, the rest of the chat contained filler phrases.
The dull conversation got exciting every now and then when the chat bot was asking questions reacting to the key words in the speech of the chat partner. For example, if you said “My father hates me,” the bot would ask “Who else in the family does hate you?” Of course, there was no deep analysis of the words’ meaning. All the words, used by the chat partner were just a set of character data. However, ELIZA chat bot made a great impact on the future of chat, or chatter, bots, showing that it was possible to mess with the human language and to create some imitation.
1972 the psychiatrist Kenneth Colby wrote another program, his answer to ELIZA. His chat bot, PARRY, imitated communication style of a paranoid schizophrenic. A few times ELIZA and PARRY were given a chance to communicate with each other. Since that time making bots “talk” to each other has become one of the favorite time passing of chat bots’ developers.
Some time later, a number of computer games used the ELIZA’s algorithm, but it was way later, already in the 21st century, when perfect environment for chat bots was found. We are talking now about instant messaging. It all started with Kevin Fox’ AOLiza which again used the same algorithm as our dear friend, ELIZA. In a way it was a very successful experience since many IM users were accustomed to random chat partners and excessive use of bastardized language. Senseless answers of the bot did not discourage people and they tried to search for some meaning in them. Fox’ experiment was very important for the future development of similar programs. Nowadays you can find a lot of chat bots in each IM network, some of them were specially created to mention a certain brand in the conversation.
Testing for Humanity
It is supposed that the ideal chat bot should be able to pass Turing Test. There are even yearly competitions for such programs. The most well-known of them is Loebner Prize.
Turing test was mentioned for the first time by (as the name suggests it) Alan Turing in 1950 in his article “Computing Machinery and Intelligence.” The test is designed to testing the computer for having human intelligence. The idea was to see if computer can “think”. The process goes as following. A human judge is talking with two chat partners, one is human, and the other is computer. The task of the judge is to figure out who is who. If he/she can’t give a definite answer, then it means computer passes the test.
Chat Bots of the 21st century
Loebner Prize encourages developments of chat bots. However, till now there are not many chat bots that are close to leading a “human” conversation. There are two favorites as of now Jabberwacky, A.L.I.C.E. (Artificial Linguistic Internet Computer Entity) and D.U.D.E.. They are constantly developing, learning new responses and trying to take advantage of new technologies.
Chat Bots in Business
A great number of companies that have active internet presence use the technology in their best interests. Chat bots are used as virtual assistants that can answer customer’s questions, help the companies to accomplish their marketing purpose, maintain their twitter accounts.
Future of Chat Bots
More and more developers try to get close to grasping the idea of artificial intelligence. For them there is no question whether they succeed or not. The question is when they will be able to create a computer program that will act, think and talk like a human. And what will be the consequences. Till then the developers will make more attempts in improving existing chat bots and creating new ones. How much time it will take them nobody knows. But better watch out, maybe your new best online friend is a bot.
But then again, maybe not.
Saturday, February 12, 2011
Chat bots review 2
Thousands of people want to know; is a Chat Bot a real benefit or are Chat Bots an invasion to the Internet? Is it a hoax, a toy, a gimmick, an automated employee, or a business asset? In many ways they are all of that. Let’s start with what Chat Bots are and how this all began.
DEFINITION
A Chat Bot is an artificial intelligence, a “living entity” designed to have conversations with real human beings. Some Chat Bots appear as males, some appear females, some are robots, and some have a fantasy-like appearance. They all have one important thing in common; they are programmed so a “Chat Bot” can respond to human! They appear to talk, to be so intelligent, and responsive they become almost real to the person they are talking to. There are over 575 Chat Bots, used in real businesses throughout the world in 20 countries.
HOW IT ALL BEGAN
It all began in the early 1960’s when Joseph Weizenbaum joined the MIT Artificial Intelligence Lab. When he developed “ELIZA”, she was simply an automated computer program that could respond to people. She was and still is today programmed as a Rogerian Psychotherapist; at best a semi-intelligent Chat Bot, having conversations with humans.
ELIZA was first presented to a group of highly intelligent, computer science technologists who knew she was a computer software program. The longer their conversations with her continued, although she responded to them by the simple illusion of understanding, the more the participants seemed to forget she was not real. They became so emotionally involved that one person cried at the responses from ELIZA.
Weizenbaum was so shocked by how quickly people became emotionally involved with ELIZA he perceived “HER” as a threat and he seriously considered shutting down the early ELIZA program. He stated, “This is a rare experience in the history of computer science.”
Instead he wrote a book about the whole experience, published in 1972, called Computer Power and Human Reason. While at the time it was an excellent resource for the public who were primarily uninvolved with computers; today, with even children in preschool learning about computers, it would be more like the content in “Computer for Dummies.”
Yet perhaps he was right in thinking about shutting down this project. Just as with anything in life; there are benefits and yet some distinct disadvantages to a Chat Bot. The question is do the advantages outweigh the disadvantages? Can the public be kept safe from the malicious Chat Bots?
ADVANTAGES FOR BUSINESSES
One of the biggest benefits is for a business to save money by cutting the cost of employment in their customer service departments. When normal customer service departments are unavailable, Service Chat Bots or Virtual Assistants can answer many customer questions.
Site Chat Bots are interactive, lifelike, conversational agents capable of interacting on your website with your customers. We can see how much Site Chat Bots can benefit companies as with Virtual Assistant, Malgorzata Podkowa – Domanska, who is an Interior Designer for Barlinek SA, one of the biggest manufacturers of natural wooden flooring's in the world. Their Service Chat Bot, Wiktoria, can give advice about wooden flooring's such as How to lay and glue floorboard? How to clean the floor? What is needed to lay the floor? She can also answer many other questions about Barlinek SA products when Malgorzata is unavailable. Another feature of Site Chat Bots is you can use them for Live Chats. They will sit on your site “talking” to customers 24 hours a day, 7 days a week processing data and assisting customers.
ADVANTAGES FOR ENTERTAINMENT
For entertainment purposes, a Game Chat Bot can react to the player of the game, thus responding to key plays to keep a game more demanding, challenging, rewarding, and therefore fun. As technology has evolved, so have the challenges of gaming to the point that thousands of ADULTS now play as many games as children. The gaming industry now sells millions of dollars in games.
DISADVANTAGES
CHAT BOTS have also become such a nightmare to Internet chatters, that while they do have some entertainment value, it is difficult to distinguish between people and Chat Bots. Now there are even programs to allow anyone to make their own Chat Bot.
As published in the Washington Post by Computer Security Expert, Brian Krebs, August 24, 2007, “A large number of Yahoo!’s instant messenger chat rooms are being overrun by … “Chat Bots”… automated programs designed to hawk commercial services, Web sites, and other wares, even porn sites thus preventing millions of actual human users from joining most of the chat rooms…”
YAHOO, MSN, AND AIM are very aware they have invaded their numerous chat rooms, and thousands of people are aware of the nuisance of Chat Bots. Often with people in the chat rooms cannot be sure they are talking with a real person or are they talking with a Chat Bot?
So you will have to be the judge… Are Chat Bots an advantage or a disadvantage to the public?
DEFINITION
A Chat Bot is an artificial intelligence, a “living entity” designed to have conversations with real human beings. Some Chat Bots appear as males, some appear females, some are robots, and some have a fantasy-like appearance. They all have one important thing in common; they are programmed so a “Chat Bot” can respond to human! They appear to talk, to be so intelligent, and responsive they become almost real to the person they are talking to. There are over 575 Chat Bots, used in real businesses throughout the world in 20 countries.
HOW IT ALL BEGAN
It all began in the early 1960’s when Joseph Weizenbaum joined the MIT Artificial Intelligence Lab. When he developed “ELIZA”, she was simply an automated computer program that could respond to people. She was and still is today programmed as a Rogerian Psychotherapist; at best a semi-intelligent Chat Bot, having conversations with humans.
ELIZA was first presented to a group of highly intelligent, computer science technologists who knew she was a computer software program. The longer their conversations with her continued, although she responded to them by the simple illusion of understanding, the more the participants seemed to forget she was not real. They became so emotionally involved that one person cried at the responses from ELIZA.
Weizenbaum was so shocked by how quickly people became emotionally involved with ELIZA he perceived “HER” as a threat and he seriously considered shutting down the early ELIZA program. He stated, “This is a rare experience in the history of computer science.”
Instead he wrote a book about the whole experience, published in 1972, called Computer Power and Human Reason. While at the time it was an excellent resource for the public who were primarily uninvolved with computers; today, with even children in preschool learning about computers, it would be more like the content in “Computer for Dummies.”
Yet perhaps he was right in thinking about shutting down this project. Just as with anything in life; there are benefits and yet some distinct disadvantages to a Chat Bot. The question is do the advantages outweigh the disadvantages? Can the public be kept safe from the malicious Chat Bots?
ADVANTAGES FOR BUSINESSES
One of the biggest benefits is for a business to save money by cutting the cost of employment in their customer service departments. When normal customer service departments are unavailable, Service Chat Bots or Virtual Assistants can answer many customer questions.
Site Chat Bots are interactive, lifelike, conversational agents capable of interacting on your website with your customers. We can see how much Site Chat Bots can benefit companies as with Virtual Assistant, Malgorzata Podkowa – Domanska, who is an Interior Designer for Barlinek SA, one of the biggest manufacturers of natural wooden flooring's in the world. Their Service Chat Bot, Wiktoria, can give advice about wooden flooring's such as How to lay and glue floorboard? How to clean the floor? What is needed to lay the floor? She can also answer many other questions about Barlinek SA products when Malgorzata is unavailable. Another feature of Site Chat Bots is you can use them for Live Chats. They will sit on your site “talking” to customers 24 hours a day, 7 days a week processing data and assisting customers.
ADVANTAGES FOR ENTERTAINMENT
For entertainment purposes, a Game Chat Bot can react to the player of the game, thus responding to key plays to keep a game more demanding, challenging, rewarding, and therefore fun. As technology has evolved, so have the challenges of gaming to the point that thousands of ADULTS now play as many games as children. The gaming industry now sells millions of dollars in games.
DISADVANTAGES
CHAT BOTS have also become such a nightmare to Internet chatters, that while they do have some entertainment value, it is difficult to distinguish between people and Chat Bots. Now there are even programs to allow anyone to make their own Chat Bot.
As published in the Washington Post by Computer Security Expert, Brian Krebs, August 24, 2007, “A large number of Yahoo!’s instant messenger chat rooms are being overrun by … “Chat Bots”… automated programs designed to hawk commercial services, Web sites, and other wares, even porn sites thus preventing millions of actual human users from joining most of the chat rooms…”
YAHOO, MSN, AND AIM are very aware they have invaded their numerous chat rooms, and thousands of people are aware of the nuisance of Chat Bots. Often with people in the chat rooms cannot be sure they are talking with a real person or are they talking with a Chat Bot?
So you will have to be the judge… Are Chat Bots an advantage or a disadvantage to the public?
Tuesday, February 8, 2011
Chatbot review 1
A chat bot, also known as a chatter bot, is a computer program that stimulates real-time conversation with one or more adults. It uses hearing as well as text to communicate with human beings. The word 'chatterbot' was coined by the creator of the first talking robot, Michael Mauldin. The basis of these programs come from a paper written by Alan Turing and titled 'Computing Machinery and Intelligence.' In this paper, he talks about computer systems that can take the place of humans in a real-time conversation with other human beings. Based on this idea, many individuals and companies started to write programs and these came to be known as chat bots.
Chat bots are used for many practical purposes today. It is used to provide online help to users, act as a virtual assistant, extend personalized service to customers and be a talking companion to anyone who is looking for some company. They have become popular in many fields and have replaced human beings as customer service representatives in many online sites.
Numerous chat bots are existing today to perform different functions in many countries. We will review some of them in this article.
ELIZA
ELIZA is one of the best-known chat bots. It was developed in 1960s and is one of the first examples of artificial intelligence programs. In those days, many people even mistook her to be a human being. This program was developed by Joseph Weizenbaum of MIT University and was used to simulate a Rogerian Psychotherapist. The program used text as the only means of conversation and she could give intelligent answers to questions that were related to the personal life and family of an individual, including the problems and concerns that was faced by an individual.
This program matched string patterns to ask questions and provide comforting answers to the individuals. A typical converstaion can be:
User : I am feeling sick
ELIZA: How long have you been feeling sick
User: For a week now.
ELIZA : Tell me more...
When the above conversation is analyzed, one can see that the string was matched with another question and for anything that ELIZA did not understand, there were generic replies like ”Tell me more..” or ”I do not understand you fully” or ”Elaborate on that.”
Though it was an elementary idea of artificial intelligence, the beauty lies in its simplicity. There are no complicated algorithms involved and it used a simple idea of pattern matching. ELIZA took the world of Internet and AI by storm. She was the first step in showing the world a glimpse of the potential of AI. This led many individuals to work on similar programs and this led to more and more advanced AI programs that could mimic human beings in every way.
ANN
Ann is a virtual assistant who represents Aetna, the US Health-care company. She can help users to find the information they are looking for on the website and can also help them with logging in. She can even help users with the registration process and retrieve lost or forgotten passwords. Users get the service that is similar to talking to a customer service representative over the phone. This program is available round the clock and is interactive.
ISIDORA
Isidora is a chat bot and virtual assistant used by Kraft Foods. She can answer questions regarding the different products and help users find the information they want on the website. She also asks questions and makes users feel that they are talking to a real person and not a chat bot. She also helps the HR team to make product presentations and to convey important messages using the different multimedia options like audio and video. The unique aspect about this program is that it is a video-generated AI program that can interact intelligently with all customers.
The above-mentioned examples give an idea of how AI has been used to provide a better customer experience. From the companies' point of view, it is a lot of savings. They can save on the salary and benefits paid to humdreds of customer service agents to provide round the clock assistance to customers. These programs have replaced many interaction-based jobs around the world.
In short, chat bots are a perfect example of AI and its uses in the real-world. It provides great customer service at little or no maintanence cost to the companies. It is also the first step in the world of AI and its huge potential that can benefit mankind in a profound way in the future.
Chat bots are used for many practical purposes today. It is used to provide online help to users, act as a virtual assistant, extend personalized service to customers and be a talking companion to anyone who is looking for some company. They have become popular in many fields and have replaced human beings as customer service representatives in many online sites.
Numerous chat bots are existing today to perform different functions in many countries. We will review some of them in this article.
ELIZA
ELIZA is one of the best-known chat bots. It was developed in 1960s and is one of the first examples of artificial intelligence programs. In those days, many people even mistook her to be a human being. This program was developed by Joseph Weizenbaum of MIT University and was used to simulate a Rogerian Psychotherapist. The program used text as the only means of conversation and she could give intelligent answers to questions that were related to the personal life and family of an individual, including the problems and concerns that was faced by an individual.
This program matched string patterns to ask questions and provide comforting answers to the individuals. A typical converstaion can be:
User : I am feeling sick
ELIZA: How long have you been feeling sick
User: For a week now.
ELIZA : Tell me more...
When the above conversation is analyzed, one can see that the string was matched with another question and for anything that ELIZA did not understand, there were generic replies like ”Tell me more..” or ”I do not understand you fully” or ”Elaborate on that.”
Though it was an elementary idea of artificial intelligence, the beauty lies in its simplicity. There are no complicated algorithms involved and it used a simple idea of pattern matching. ELIZA took the world of Internet and AI by storm. She was the first step in showing the world a glimpse of the potential of AI. This led many individuals to work on similar programs and this led to more and more advanced AI programs that could mimic human beings in every way.
ANN
Ann is a virtual assistant who represents Aetna, the US Health-care company. She can help users to find the information they are looking for on the website and can also help them with logging in. She can even help users with the registration process and retrieve lost or forgotten passwords. Users get the service that is similar to talking to a customer service representative over the phone. This program is available round the clock and is interactive.
ISIDORA
Isidora is a chat bot and virtual assistant used by Kraft Foods. She can answer questions regarding the different products and help users find the information they want on the website. She also asks questions and makes users feel that they are talking to a real person and not a chat bot. She also helps the HR team to make product presentations and to convey important messages using the different multimedia options like audio and video. The unique aspect about this program is that it is a video-generated AI program that can interact intelligently with all customers.
The above-mentioned examples give an idea of how AI has been used to provide a better customer experience. From the companies' point of view, it is a lot of savings. They can save on the salary and benefits paid to humdreds of customer service agents to provide round the clock assistance to customers. These programs have replaced many interaction-based jobs around the world.
In short, chat bots are a perfect example of AI and its uses in the real-world. It provides great customer service at little or no maintanence cost to the companies. It is also the first step in the world of AI and its huge potential that can benefit mankind in a profound way in the future.
Subscribe to:
Posts (Atom)