Computer learns language by playing games
From the post:
Computers are great at treating words as data: Word-processing programs let you rearrange and format text however you like, and search engines can quickly find a word anywhere on the Web. But what would it mean for a computer to actually understand the meaning of a sentence written in ordinary English — or French, or Urdu, or Mandarin?
One test might be whether the computer could analyze and follow a set of instructions for an unfamiliar task. And indeed, in the last few years, researchers at MIT’s Computer Science and Artificial Intelligence Lab have begun designing machine-learning systems that do exactly that, with surprisingly good results.
The original paper, Learning to Win by Reading Manuals in a Monte-Carlo Framework by S.R.K. Branavan, David Silver, and, Regina Barzilay reports:
Abstract:
This paper presents a novel approach for leveraging automatically extracted textual knowledge to improve the performance of control applications such as games. Our ultimate goal is to enrich a stochastic player with high level guidance expressed in text. Our model jointly learns to identify text that is relevant to a given game state in addition to learning game strategies guided by the selected text. Our method operates in the Monte-Carlo search framework, and learns both text analysis and game strategies based only on environment feedback. We apply our approach to the complex strategy game Civilization II using the official game manual as the text guide. Our results show that a linguistically-informed game-playing agent significantly outperforms its language-unaware counterpart, yielding a 27% absolute improvement and winning over 78% of games when playing against the built-in AI of Civilization II.
Deeply interesting work, particularly as assistive authoring for topic maps.
Think about the number of recipes, manuals, IETMs, etc., that are in electronic format. Identifying common steps, despite differences in descriptions, could be quite useful.
Come to think of it, most regulations and laws are written that way. Imagine the difference between a strictly textual search of legal resources and a semantically aware search of legal resources? Not today or tomorrow, but given the rate of progression, that sort of killer app may not be far off.
Do you want to be selling it or buying it?
Sci-fi fans take note:
Games are won by gaining control of the entire world map.