Models of Co-occurrence
Abstract
A model of co-occurrence in bitext is a boolean predicate that indicates whether a given pair of word tokens co-occur in corresponding regions of the bitext space. Co-occurrence is a precondition for the possibility that two tokens might be mutual translations. Models of co-occurrence are the glue that binds methods for mapping bitext correspondence with methods for estimating translation models into an integrated system for exploiting parallel texts. Different models of co-occurrence are possible, depending on the kind of bitext map that is available, the language-specific information that is available, and the assumptions made about the nature of translational equivalence. Although most statistical translation models are based on models of co-occurrence, modeling co-occurrence correctly is more difficult than it may at first appear.
Keywords
Cite
@article{arxiv.cmp-lg/9805003,
title = {Models of Co-occurrence},
author = {I. Dan Melamed},
journal= {arXiv preprint arXiv:cmp-lg/9805003},
year = {2007}
}