Lexical Attraction Models of Language

Deniz Yuret (2006) (PDF)
Lexical Attraction Models of Language. Still unpublished.


This paper presents on-going work on the lexical attraction models of language, in which the only explicitly represented linguistic knowledge is the likelihood of pairwise relations between words. This is in contrast with models that represent linguistic knowledge in terms of a lexicon, which assigns categories to each word, and a grammar, which expresses possible combinations in terms of these categories. The word-based nature and the simplicity of lexical attraction models make them good candidates for experiments in language learning. I introduce a parser and an on-line unsupervised learning algorithm based on expectation maximization.