ELIZA: A Computer Program for the Study of Natural Language Communication Between Man and Machine

Introduction

1. What is ELIZA?
   A program (in MAD-SLIP on MIT’s MAC time-sharing system) that makes certain kinds of natural-language conversation between a person and a computer possible: the user types statements, ELIZA analyses them and types a response.
   • Weizenbaum, 1966, ELIZA (Communications of the ACM), Introduction
2. Why did Weizenbaum name the program ELIZA?
   After Eliza Doolittle of Pygmalion: its language abilities can be continually improved by a “teacher”, and it can be made to appear ever more civilized, “the relation of appearance to reality, however, remaining in the domain of the playwright.”
   • Weizenbaum, 1966, ELIZA (Communications of the ACM), Introduction
3. What maxim opens the ELIZA paper, and what was the paper’s purpose?
   “To explain is to explain away”: once a seemingly intelligent program’s inner workings are explained plainly, its magic crumbles and it moves from the shelf marked “intelligent” to the one for curios. The paper aims to cause just such a re-evaluation of ELIZA.
   • Weizenbaum, 1966, ELIZA (Communications of the ACM), Introduction
4. What is ELIZA’s gross procedure?
   Read the input and look for a keyword. If one is found, transform the sentence by a rule associated with the keyword; if not, print a content-free remark or, under certain conditions, an earlier transformation. Print the result.
   • Weizenbaum, 1966, ELIZA (Communications of the ACM), Introduction
5. How does ELIZA limit the input it transforms to a single phrase or sentence?
   Commas and periods are delimiters: if a keyword has already been found, everything after the delimiter is deleted; if not, the text up to and including the delimiter is deleted. So only one phrase or sentence is ever transformed.
   • Weizenbaum, 1966, ELIZA (Communications of the ACM), Introduction
6. What is an ELIZA script, and why does it matter that a script is data?
   The keywords and their transformation rules for a class of conversation. Because the script is data, not part of the program, ELIZA isn’t tied to particular patterns or responses, or even one language: scripts existed in Welsh and German as well as English.
   • Weizenbaum, 1966, ELIZA (Communications of the ACM), Introduction
7. What five technical problems did ELIZA have to solve?
   (1) Identifying the most important keyword in the input; (2) identifying some minimal context around it (e.g. “you” followed by “are” signals an assertion); (3) choosing and applying a transformation rule; (4) responding sensibly when there are no keywords; (5) making scripts easy to edit and extend.
   • Weizenbaum, 1966, ELIZA (Communications of the ACM), Introduction