Models of Co-occurrence

Details Models of Co-occurrence Models of Co-occurrence

1998-05-08

arxiv.org/abs/cmp-lg/9805003v1

Computer Science

Computation and Language

Scientific paper

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.

Affiliated with

Also associated with

No associations

Rating

Models of Co-occurrence does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.

If you have personal experience with Models of Co-occurrence, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Models of Co-occurrence will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-202401