| ELIZA | |
|---|---|
 A conversation with ELIZA | |
| Original author | Joseph Weizenbaum |
| Developer | MIT |
| Initial release | 1966; 60 years ago (1966) |
| Written in | MAD-SLIP |
| Operating system | CTSS |
| Platform | IBM 7094 |
| Type | Chatbot |
| License | Public domain |
| Website | elizagen |
ELIZA is an earlynatural language processingcomputer program developed from 1964 to 1967[1] atMIT byJoseph Weizenbaum.[2][3][page needed] Created to explore communication between humans and machines, ELIZA simulated conversation by using apattern matching and substitutionmethodology that gave users an illusion ofunderstanding on the part of the program, but had no representation that could be considered really understanding what was being said by either party.[4][5][6] Whereas the ELIZA program itself was written (originally)[7] inMAD-SLIP, the pattern matching directives that contained most of its language capability were provided in separate "scripts", represented in alisp-like representation.[8] The most famous script, DOCTOR, simulated apsychotherapist of the Rogerian school (in which the therapist often reflects back the patient's words to the patient),[9][10][11] and used rules, dictated in the script, to respond with non-directional questions to user inputs. As such, ELIZA was one of the firstchatbots (originally "chatterbots") and one of the first programs capable of attempting theTuring test.[12][13]
Weizenbaum intended the program as a method to explore communication between humans and machines. He was surprised that some people, including his secretary, attributed human-like feelings to the computer program,[3][page needed] a phenomenon that came to be called theELIZA effect. Many academics believed that the program would be able to positively influence the lives of many people, particularly those with psychological issues, and that it could aid doctors working on such patients' treatment.[3][page needed][14] While ELIZA was capable of engaging in discourse, it could not converse with true understanding.[15] However, many early users were convinced of ELIZA's intelligence and understanding, despite Weizenbaum's insistence to the contrary.[6]
The original ELIZAsource code had been missing since its creation in the 1960s, as it was not common to publish articles that included source code at that time. However, more recently the MAD-SLIP source code was discovered in the MIT archives and published on various platforms, such as theInternet Archive.[16] The source code is of high historical interest since it demonstrates not only the specificity of programming languages and techniques at that time, but also the beginning of software layering and abstraction as a means of achieving sophisticated software programming.
.jpg)
Joseph Weizenbaum's ELIZA, running the DOCTOR script, created a conversational interaction somewhat similar to what might take place in the office of "a [non-directive] psychotherapist in an initial psychiatric interview"[17] and to "demonstrate that the communication between man and machine was superficial".[18] While ELIZA is best known for acting in the manner of a psychotherapist, the speech patterns are due to the data and instructions supplied by the DOCTOR script.[19] ELIZA itself examined the text for keywords, applied values to said keywords, and transformed the input into an output; the script that ELIZA ran determined the keywords, set the values of keywords, and set the rules of transformation for the output.[20] Weizenbaum chose to make the DOCTOR script in the context of psychotherapy to "sidestep the problem of giving the program a data base of real-world knowledge",[3][page needed] allowing it to reflect back the patient's statements to carry the conversation forward.[3][page needed] The result was a somewhat intelligent-seeming response that reportedly deceived some early users of the program.[21]
Weizenbaum named his program ELIZA afterEliza Doolittle, a working-class character inGeorge Bernard Shaw'sPygmalion (also appearing in the musicalMy Fair Lady, which was based on the play and was hugely popular at the time). According to Weizenbaum, ELIZA's ability to be "incrementally improved" by various users made it similar to Eliza Doolittle,[20] since Eliza Doolittle was taught to speak with anupper-classaccent in Shaw's play.[9][22] However, unlike the human character in Shaw's play, ELIZA is incapable of learning new patterns of speech or new words through interaction alone. Edits must be made directly to ELIZA's active script in order to change the manner by which the program operates.
Weizenbaum first implemented ELIZA in his ownSLIP list-processing language, where, depending upon the initial entries by the user, the illusion of human intelligence could appear, or be dispelled through several interchanges.[2] Some of ELIZA's responses were so convincing that Weizenbaum and several others have anecdotes of users becoming emotionally attached to the program, occasionally forgetting that they were conversing with a computer.[3][page needed] Weizenbaum's own secretary reportedly asked Weizenbaum to leave the room so that she and ELIZA could have a real conversation. Weizenbaum was surprised by this, later writing: "I had not realized ... that extremely short exposures to a relatively simple computer program could induce powerful delusional thinking in quite normal people."[23]
In 1966, interactive computing (via a teletype) was new. It was 11 years before the personal computer became familiar to the general public, and three decades before most people encountered attempts atnatural language processing in Internet services likeAsk.com or PC help systems such as Microsoft OfficeClippit.[24] Although those programs included years of research and work, ELIZA remains a milestone 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.[25]
At theICCC 1972, ELIZA was brought together with another early artificial-intelligence program namedPARRY for a computer-only conversation. While ELIZA was built to speak as a doctor, PARRY was intended to simulate a patient withschizophrenia.[26]
Weizenbaum originally wrote ELIZA in MAD-SLIP forCTSS on anIBM 7094 as a program to make natural-language conversation possible with a computer.[27] To accomplish this, Weizenbaum identified five "fundamental technical problems" for ELIZA to overcome: the identification of key words, the discovery of a minimal context, the choice of appropriate transformations, the generation of responses in the absence of key words, and the provision of an editing capability for ELIZA scripts.[20] Weizenbaum solved these problems and made ELIZA such that it had no built-in contextual framework or universe of discourse.[19] However, this required ELIZA to have a script of instructions on how to respond to inputs from users.[6]
ELIZA starts its process of responding to an input by a user by first examining the text input for a "keyword".[5] A "keyword" is a word designated as important by the acting ELIZA script, which assigns to each keyword a precedence number, or a RANK, designed by the programmer.[15] If such words are found, they are put into a "keystack", with the keyword of the highest RANK at the top. The input sentence is then manipulated and transformed as the rule associated with the keyword of the highest RANK directs.[20] For example, when the DOCTOR script encounters words such as "alike" or "same", it would output a message pertaining to similarity, in this case "In what way?",[4] as these words had high precedence number. This also demonstrates how certain words, as dictated by the script, can be manipulated regardless of contextual considerations, such as switching first-person pronouns and second-person pronouns and vice versa, as these too had high precedence numbers. Such words with high precedence numbers are deemed superior to conversational patterns and are treated independently of contextual patterns.[citation needed]
Following the first examination, the next step of the process is to apply an appropriate transformation rule, which includes two parts: the "decomposition rule" and the "reassembly rule".[20] First, the input is reviewed for syntactical patterns in order to establish the minimal context necessary to respond. Using the keywords and other nearby words from the input, different disassembly rules are tested until an appropriate pattern is found. Using the script's rules, the sentence is then "dismantled" and arranged into sections of the component parts as the "decomposition rule for the highest-ranking keyword" dictates. The example that Weizenbaum gives is the input "You are very helpful", which is transformed to "I are very helpful". This is then broken into (1) empty (2) "I" (3) "are" (4) "very helpful". The decomposition rule has broken the phrase into four small segments that contain both the keywords and the information in the sentence.[20]
The decomposition rule then designates a particular reassembly rule, or set of reassembly rules, to follow when reconstructing the sentence.[5] The reassembly rule takes the fragments of the input that the decomposition rule had created, rearranges them, and adds in programmed words to create a response. Using Weizenbaum's example previously stated, such a reassembly rule would take the fragments and apply them to the phrase "What makes you think I am (4)", which would result in "What makes you think I am very helpful?". This example is rather simple, since depending upon the disassembly rule, the output could be significantly more complex and use more of the input from the user. However, from this reassembly, ELIZA then sends the constructed sentence to the user in the form of text on the screen.[20]
These steps represent the bulk of the procedures that ELIZA follows in order to create a response from a typical input, though there are several specialized situations that ELIZA/DOCTOR can respond to. One Weizenbaum specifically wrote about was when there is no keyword. One solution was to have ELIZA respond with a remark that lacked content, such as "I see" or "Please go on".[20] The second method was to use a "MEMORY" structure, which recorded prior recent inputs, and would use these inputs to create a response referencing a part of the earlier conversation when encountered with no keywords.[28] This was possible due to Slip's ability to tag words for other usage, which simultaneously allowed ELIZA to examine, store, and repurpose words for usage in outputs.[20]
While these functions were all framed in ELIZA's programming, the exact manner by which the program dismantled, examined, and reassembled inputs is determined by the operating script. The script is not static and can be edited, or a new one created, as is necessary for the operation in the context needed. This would allow the program to be applied in multiple situations, including the well-known DOCTOR script, which simulates a Rogerian psychotherapist.[16]
ALisp version of ELIZA, based on Weizenbaum's CACM paper, was written shortly after that paper's publication by Bernie Cosell.[29][30] ABASIC version appeared inCreative Computing in 1977 (although it was written in 1973 by Jeff Shrager).[31] This version, which was ported to many of the earliest personal computers, appears to have been subsequently translated into many other versions in many other languages. Shrager claims not to have seen either Weizenbaum's or Cosell's versions.
In 2021, Jeff Shrager searched MIT's Weizenbaum archives, along withMIT archivist Myles Crowley, and found files labeled Computer Conversations. These included the complete source code listing of ELIZA in MAD-SLIP, with the DOCTOR script attached. The Weizenbaum estate gave permission to open-source this code under aCreative Commons CC0public domain license. The code and other information can be found on the ELIZAGEN site.[30] The 1965 source code has been dated as part of a software archaeology project which brings together researchers fromUSC,University of Sussex,Oxford, andStanford University, who have worked together to unravel the complicated history of ELIZA.[32]
In December 2024, Rupert Lane, with the assistance of several other engineers who had been studying the original MAD-SLIP ELIZA, brought up the original ELIZA and demonstrated that the implementation of ELIZA based on the discovered code can reproduce almost exactly the published conversations with ELIZA from Weizenbaum's 1966 paper. This original ELIZA was reconstructed using the vast majority of the 1965 version of the source code: approximately 96% of the functions.[33] This was run on a version of the original MITCTSS running on a7094 emulator, both of the latter due to David Pitts.[34][35]
Another version of Eliza popular among software engineers is the version that comes with the default release ofGNU Emacs, and which can be accessed by typingM-x doctor from most modernEmacs implementations.
From Figure 15.5, Chapter 15 of Speech and Language Processing (third edition).[36]
function ELIZA GENERATOR(usersentence) returnsresponse Letw be the word insentence that has the highest keyword rank ifw exists Let r be the highest ranked rule for w that matches sentenceresponse ← Apply the transform inr tosentence if w = 'my'future ← Apply a transformation from the ‘memory’ rule list tosentence Pushfuture onto the memory queue else (no keyword applies) Eitherresponse ← Apply the transform for the NONE keyword tosentence Orresponse ← Pop the oldest response from the memory queue Returnresponse
Lay responses to ELIZA were disturbing to Weizenbaum and motivated him to write his bookComputer Power and Human Reason: From Judgment to Calculation, in which he explains the limits of computers, as he wants to make clear his opinion that the anthropomorphic views of computers are just a reduction of human beings or any life form for that matter.[37] In the independent documentary filmPlug & Pray (2010) Weizenbaum said that only people who misunderstood ELIZA called it a sensation.[38]
David Avidan, who was fascinated with future technologies and their relation to art, desired to explore the use of computers for writing literature. He conducted several conversations with anAPL implementation of ELIZA and published them – in English, and in his own translation toHebrew – under the titleMy Electronic Psychiatrist – Eight Authentic Talks with a Computer. In the foreword, he presented it as a form ofconstrained writing.[39]
There are many programs based on ELIZA in different programming languages. ForMS-DOS computers, someSound Blaster cards came bundled withDr. Sbaitso, which functions like the DOCTOR script. Other versions adapted ELIZA around a religious theme, such as ones featuring Jesus (both serious and comedic), and another Apple II variant calledI Am Buddha. The 1980 gameThe Prisoner incorporated ELIZA-style interaction within its gameplay. In 1988, the British artist and friend of WeizenbaumBrian Reffin Smith created two art-oriented ELIZA-style programs written inBASIC, one called "Critic" and the other "Artist", running on two separateAmiga 1000 computers and showed them at the exhibition "Salamandre" in the Musée du Berry,Bourges, France. The visitor was supposed to help them converse by typing in to "Artist" what "Critic" said, and vice versa. The secret was that the two programs were identical.GNU Emacs formerly had apsychoanalyze-pinheadcommand that simulates a session between ELIZA andZippy the Pinhead.[40] The Zippyisms were removed due to copyright issues, but the DOCTOR program remains.
ELIZA has been referenced in popular culture and continues to be a source of inspiration for programmers and developers focused on artificial intelligence. It was also featured in a 2012 exhibit atHarvard University titled "Go AskA.L.I.C.E.", as part of a celebration of mathematicianAlan Turing's 100th birthday. The exhibit explores Turing's lifelong fascination with the interaction between humans and computers, pointing to ELIZA as one of the earliest realizations of Turing's ideas.[1]
ELIZA won a 2021 LegacyPeabody Award. A 2023preprint reported that ELIZA beatOpenAI'sGPT-3.5, the model used byChatGPT at the time, in aTuring test study. However, it did not outperformGPT-4 or real humans.[41][42]
The Eliza effect borrowed its name from ELIZA the chatbot. This effect is first defined inFluid Concepts and Creative Analogies: Computer Models and the Fundamental Mechanisms of Thought[43] as humans' interpretations that some computer programs understand the user inputs and make analogies.
These interpretations can potentially manipulate and misinform users. When interacting and communicating with chatbots, users can be overly confident in the reliability of the chatbots' answers. Other than misinforming, the chatbot's human-mimicking nature can also cause severe consequences, especially for younger users who lack a sufficient understanding of the chatbot's mechanism.
Joe Wiezenbaum's most famous CTSS project was ELIZA
