Question Answering

Systems that Answer Questions Correctly

AITopics > Natural Language > Question Answering

Definition of the Area

"Questions are asked and answered every day. Question answering (QA) technology aims to deliver the same facility online. It goes further than the more familiar search based on keywords (as in Google, Yahoo, and other search engines), in attempting to recognize what a question expresses and to respond with an actual answer. This simplifies things for users in two ways. First, questions do not often translate into a simple list of keywords. ...Second, QA takes responsibility for providing answers, rather than a searchable list of links to potentially relevant documents (web pages), highlighted by snippets of text that show how the query matched the documents." From Webber&Webb 2010 (below).

Good Places to Start

Overview article by B.Webber and N.Webb -downloadable pdf file - (2010). In Blackwell's Handbook of Computational Linguistics and Natural Language Processing.

Individual QA Systems

BASEBALL

BASEBALL: AN AUTOMATIC QUESTION ANSWERER Green, Bert F. Jr., Alice K. Wolf, Carol Chomsky, and Kenneth Laughery. In Computers and Thought (1963).

DEDUCTIVE QUESTION_ANSWERING SYSTEM

Black (1964)

LUNAR

Woods (1970-) See Woods - Semantics for a Question Answering System (1968)

PROTOSYNTHEX

Simmons et al (1963)

SAD SAM

INFERENTIAL MEMORY AS THE BASIS OF MACHINES WHICH UNDERSTAND NATURAL LANGUAGE Robert K. Lindsay. In Computers and Thought (1963).

SHRDLU

SHRDLU, one of the early AI programs, which goes beyond simple question-answering. "SHRDLU is a program for understanding natural language, written by Terry Winograd at the M.I.T. Artificial Intelligence Laboratory in 1968-70. SHRDLU carried on a simple dialog (via teletype) with a user, about a small world of objects (the BLOCKS world) shown on an early display screen (DEC-340 attached to a PDP-6 computer)." See video of SHRDLU demo at MIT.

• And for fun, check out the the story of how SHRDLU got its name.

START

START. "START, the world's first Web-based question answering system, has been on-line and continuously operating since December, 1993. It has been developed by Boris Katz and his associates of the InfoLab Group at the MIT Computer Science and Artificial Intelligence Laboratory. Unlike information retrieval systems (e.g., search engines), START aims to supply users with "just the right information," instead of merely providing a list of hits. Currently, the system can answer millions of English questions about places (e.g., cities, countries, lakes, coordinates, weather, maps, demographics, political and economic systems), movies (e.g., titles, actors, directors), people (e.g., birth dates, biographies), dictionary definitions, and much, much more." Try it out at Ask a Question. Contains many links to PDF versions of publications on Question Answering and other aspects of Natural Language Processing.

STUDENT

Bobrow (1964)

WATSON

IBM Watson System