Abstract
Accounts of language processing have suggested that it requires retrieving concepts from memory
in response to an ongoing stream of information. This can be facilitated by inferring the gist of a
sentence, conversation, or document, and using that gist to predict related concepts and
disambiguate words. We analyze the abstract computational problem underlying the extraction and
use of gist, formulating this problem as a rational statistical inference. This leads us to a novel
approach to semantic representation in which word meanings are represented in terms of a set of
probabilistic topics. The topic model performs well in predicting word association and the effects
of semantic association and ambiguity on a variety of language processing and memory tasks. It
also provides a foundation for developing more richly structured statistical models of language, as
the generative process assumed in the topic model can easily be extended to incorporate other
kinds of semantic and syntactic structure.
Users
Please
log in to take part in the discussion (add own reviews or comments).