Computer Learns Language By Playing Games
Frans Faase writes "By basing its strategies on the text of a manual, a computer infers the meanings of words without human supervision. The paper Learning to Win by Reading Manuals in a Monte-Carlo Framework (PDF) explains how a computer program succeeds in playing Civilization II using the official game manual as a strategy guide. This manual uses a large vocabulary of 3638 words, and is composed of 2083 sentences, each on average 16.9 words long. By this the program improves it success rate from 45% to 78% in playing the game. No prior knowledge of the language is used."
So they've managed to create software that can process a manual, with a language it does not already understand, more effectively than my wife.
Impressive. Now they need to make it reiterate the manual in a way that she can understand.
Just another ignorant American.