In 1966, interactive computing (via a teletype) was new. It was 15 years before the personal computer became familiar to the general public, and three decades before most people encountered attempts at natural language processing in Internet services like Ask.com or PC help systems such as Microsoft Office Clippy. Although those programs included years of research and work, 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 the 1976 article "Computer Power and Human Reason," an excerpt of which is included in The New Media Reader edited by Noah Wardrip-Fruin and Nick Montfort, Weizenbaum notes how quickly and deeply people became emotionally involved with the computer program, taking offence when he asked to view the transcripts, saying it was an invasion of their privacy, even asking him to leave the room while they were working with the DOCTOR script.
ELIZA had an impact on a number of early computer games by demonstrating additional kinds of interface designs. Don Daglow wrote an enhanced version of the program called Ecala on a PDP-10 mainframe computer at Pomona College in 1973 before writing what was possibly the second or third computer role-playing game, Dungeon (1975) (The first was probably "dnd", written on and for the PLATO system in 1974, and the second may have been Moria, written in 1975). It is likely that ELIZA was also on the system where Will Crowther created Colossal Cave (Adventure), the 1975 game that spawned the interactive fiction genre. Both these games appeared some nine years after the original ELIZA.
There are many programs based on ELIZA in different languages. For example, in 1980, a company called "Don't Ask Software", founded by Randy Simon, created a version called "Abuse" for the Apple II, Atari, and Commodore PCs, which verbally abused the user based on the user's input. Other versions adapted ELIZA around a religious theme, such as ones featuring Jesus (both serious and comedic) and another Apple II variant called I Am Buddha. The 1980 game The Prisoner incorporated ELIZA-style interaction within its gameplay.
Based on http://en.wikipedia.org/wiki/ELIZA licensed under the Creative Commons Attribution-Share-Alike License 3.0
Saturday, March 12, 2011
Tuesday, March 8, 2011
ELIZA I - Who is ELIZA?
ELIZA is a computer program and an early example of primitive natural language processing. ELIZA operated by processing users' responses to scripts, the most famous of which was DOCTOR, a simulation of a Rogerian psychotherapist. Using almost no information about human thought or emotion, DOCTOR sometimes provided a startlingly human-like interaction. ELIZA was written at MIT by Joseph Weizenbaum between 1964 to 1966.
When the "patient" exceeded the very small knowledge base, DOCTOR might provide a generic response, for example, 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, but was taken seriously by several of its users, even after Weizenbaum explained to them how it worked. It was one of the first chatterbots in existence.
Weizenbaum said that ELIZA, running the DOCTOR script, provided a "parody" of "the responses of a nondirectional psychotherapist in an initial psychiatric interview." He chose the context of psychotherapy to "sidestep the problem of giving the program a data base of real-world knowledge", 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. 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, a working-class character in George Bernard Shaw's play Pygmalion, who is taught to speak with an upper-class accent.
First implemented in Weizenbaum's own SLIP list-processing language, ELIZA worked by simple parsing and substitution of key words into canned phrases. Depending upon the initial entries by the user the illusion of a human writer could be instantly dispelled, or could continue through several interchanges. 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 understanding became apparent
Lay responses to ELIZA were disturbing to Weizenbaum and motivated him to write his book Computer Power and Human Reason: From Judgment to Calculation, in which he explains the limits of computers, 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.
Based on http://en.wikipedia.org/wiki/ELIZA licensed under the Creative Commons Attribution-Share-Alike License 3.0
When the "patient" exceeded the very small knowledge base, DOCTOR might provide a generic response, for example, 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, but was taken seriously by several of its users, even after Weizenbaum explained to them how it worked. It was one of the first chatterbots in existence.
Weizenbaum said that ELIZA, running the DOCTOR script, provided a "parody" of "the responses of a nondirectional psychotherapist in an initial psychiatric interview." He chose the context of psychotherapy to "sidestep the problem of giving the program a data base of real-world knowledge", 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. 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, a working-class character in George Bernard Shaw's play Pygmalion, who is taught to speak with an upper-class accent.
First implemented in Weizenbaum's own SLIP list-processing language, ELIZA worked by simple parsing and substitution of key words into canned phrases. Depending upon the initial entries by the user the illusion of a human writer could be instantly dispelled, or could continue through several interchanges. 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 understanding became apparent
Lay responses to ELIZA were disturbing to Weizenbaum and motivated him to write his book Computer Power and Human Reason: From Judgment to Calculation, in which he explains the limits of computers, 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.
Based on http://en.wikipedia.org/wiki/ELIZA licensed under the Creative Commons Attribution-Share-Alike License 3.0
Friday, March 4, 2011
Chat Bots Use in Business
Chat bots are becoming an inevitable part of our life. People are finding more uses for them. The main purpose for them is not just entertainment anymore. They can and are being used in business, education, the gaming industry, etc.
People have always wanted to make a machine think and respond to a human as an equal, using a human language. Early results of the consistent work in this area have been promising, yet characterized by restricted vocabulary and ignorance of the real world’s complexities. However, things are changing now. Constant development of technology has resulted in the creation of several chat bots that are able to imitate human communication, in ways that was not thought to be possible earlier.
Since then, ELIZA’s time chat bots have changed a lot. Jabberwacky, A.L.I.C.E., D.U.D.E. are the names that rule the world of chat bots nowadays. While they may not engage in an entirely “human” conversation, they are good enough to delude their communication partners and pass for as human.
This ability of chat bots to conduct a limited dialogue with humans has found its ever-widening application in many areas, including today’s business.
It is not a secret that billions of calls are made yearly to customer care services of different companies. The average duration of these calls is around half a minute. Since technology is evolving the products become more complicated. Digital cameras, laptops, and cell phones are only some of the items that produce a constant flow of calls to customer care. As the products become more complex, so do the questions. This leads to an increase in the call duration.
One such call costs $4-5 to a company. Naturally, the company wants to reduce expenses. And this is where chat bots come into the picture. “Hiring” chat bots is much cheaper than hiring people to do the same job. That’s why more and more large companies decide to make use of chat bots as virtual assistants.
One of the most well-known chat bots that perform these functions is Anna (http://193.108.42.79/ikea-us/cgi-bin/ikea-us.cgi), a virtual “face” of the Swedish company IKEA. Presented with a bright positive avatar, Anna is able to answer customers’ questions, and help them choose a product in at least 18 languages. She will give you the closest IKEA shop for your location. In case your question is too complicated for her she will suggest connecting you to a human consultant.
This technology found an interesting use in the U.S. Army. Next IT designed Sergeant Star (http://sgtstar.goarmy.com/ActiveAgentUI/welcome.aspx), who can answer questions about Army life. The audience of the website is mostly young men in the age from 17 to 24 years who spend a lot of time surfing the Internet. Sergeant Star has answered over 4 million questions till date. The results of the new technology are impressive:
- average time duration spent on the website increased from 4 to 10 minutes,
- the number of questions asked doubled,
- monthly Sergeant Star responds to over 100,000 queries.
To summarize, chat bots’ employment can be beneficial in many ways. First, it reduces the costs of customer care department. Secondly, the time for dealing with one request has decreased. This means that more requests can be processed in the same time period, resulting in increased productivity. Lastly, as technology improves, the variety of tasks that chat bots can perform increases with every passing day.
Chat bots not only respond to clients’ questions but also help them make better decisions about the company’s products and services. They provide clients with information about the website’s content, guide them through relevant links, and even help them choose suitable candidates from the company’s database, in case it is a recruiting agency.
Naturally, chat bots are not perfect, and for the moment at least, they cannot completely replace humans in the field of customer care or other areas. For now they can assist humans, and they do it well. But as they evolve, the quality of their performance will be closer to that of a human worker. And considering how many people are unhappy with their ‘human’ customer care experiences, that time moment not be too distant.
People have always wanted to make a machine think and respond to a human as an equal, using a human language. Early results of the consistent work in this area have been promising, yet characterized by restricted vocabulary and ignorance of the real world’s complexities. However, things are changing now. Constant development of technology has resulted in the creation of several chat bots that are able to imitate human communication, in ways that was not thought to be possible earlier.
Since then, ELIZA’s time chat bots have changed a lot. Jabberwacky, A.L.I.C.E., D.U.D.E. are the names that rule the world of chat bots nowadays. While they may not engage in an entirely “human” conversation, they are good enough to delude their communication partners and pass for as human.
This ability of chat bots to conduct a limited dialogue with humans has found its ever-widening application in many areas, including today’s business.
It is not a secret that billions of calls are made yearly to customer care services of different companies. The average duration of these calls is around half a minute. Since technology is evolving the products become more complicated. Digital cameras, laptops, and cell phones are only some of the items that produce a constant flow of calls to customer care. As the products become more complex, so do the questions. This leads to an increase in the call duration.
One such call costs $4-5 to a company. Naturally, the company wants to reduce expenses. And this is where chat bots come into the picture. “Hiring” chat bots is much cheaper than hiring people to do the same job. That’s why more and more large companies decide to make use of chat bots as virtual assistants.
One of the most well-known chat bots that perform these functions is Anna (http://193.108.42.79/ikea-us/cgi-bin/ikea-us.cgi), a virtual “face” of the Swedish company IKEA. Presented with a bright positive avatar, Anna is able to answer customers’ questions, and help them choose a product in at least 18 languages. She will give you the closest IKEA shop for your location. In case your question is too complicated for her she will suggest connecting you to a human consultant.
This technology found an interesting use in the U.S. Army. Next IT designed Sergeant Star (http://sgtstar.goarmy.com/ActiveAgentUI/welcome.aspx), who can answer questions about Army life. The audience of the website is mostly young men in the age from 17 to 24 years who spend a lot of time surfing the Internet. Sergeant Star has answered over 4 million questions till date. The results of the new technology are impressive:
- average time duration spent on the website increased from 4 to 10 minutes,
- the number of questions asked doubled,
- monthly Sergeant Star responds to over 100,000 queries.
To summarize, chat bots’ employment can be beneficial in many ways. First, it reduces the costs of customer care department. Secondly, the time for dealing with one request has decreased. This means that more requests can be processed in the same time period, resulting in increased productivity. Lastly, as technology improves, the variety of tasks that chat bots can perform increases with every passing day.
Chat bots not only respond to clients’ questions but also help them make better decisions about the company’s products and services. They provide clients with information about the website’s content, guide them through relevant links, and even help them choose suitable candidates from the company’s database, in case it is a recruiting agency.
Naturally, chat bots are not perfect, and for the moment at least, they cannot completely replace humans in the field of customer care or other areas. For now they can assist humans, and they do it well. But as they evolve, the quality of their performance will be closer to that of a human worker. And considering how many people are unhappy with their ‘human’ customer care experiences, that time moment not be too distant.
Subscribe to:
Posts (Atom)