Models of Co-occurrence
| dc.creator | Melamed, I. Dan | |
| dc.date | 1998-05-08 | |
| dc.date.accessioned | 2026-07-07T02:36:13Z | |
| dc.date.available | 2026-07-07T02:36:13Z | |
| dc.description | 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. | |
| dc.identifier | https://arxiv.org/abs/cmp-lg/9805003 | |
| dc.identifier | http://arxiv.org/abs/cmp-lg/9805003 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/15837 | |
| dc.subject | Computation and Language | |
| dc.title | Models of Co-occurrence | |
| dc.type | text |