Models of Co-occurrence

dc.creatorMelamed, I. Dan
dc.date1998-05-08
dc.date.accessioned2026-07-07T02:36:13Z
dc.date.available2026-07-07T02:36:13Z
dc.descriptionA 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.
dc.identifierhttps://arxiv.org/abs/cmp-lg/9805003
dc.identifierhttp://arxiv.org/abs/cmp-lg/9805003
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/15837
dc.subjectComputation and Language
dc.titleModels of Co-occurrence
dc.typetext

Files

Collections