Part of Advances in Neural Information Processing Systems 15 (NIPS 2002)
Thomas Griffiths, Mark Steyvers
We explore the consequences of viewing semantic association as the result of attempting to predict the concepts likely to arise in a particular context. We argue that the success of existing accounts of semantic representation comes as a result of indirectly addressing this problem, and show that a closer correspondence to human data can be obtained by taking a probabilistic approach that explicitly models the generative structure of language.