Choosing the Word Most Typical in Context Using a Lexical Co-occurrence Network
| dc.creator | Edmonds, Philip | |
| dc.date | 1998-11-02 | |
| dc.date.accessioned | 2026-07-07T03:23:47Z | |
| dc.date.available | 2026-07-07T03:23:47Z | |
| dc.description | This paper presents a partial solution to a component of the problem of lexical choice: choosing the synonym most typical, or expected, in context. We apply a new statistical approach to representing the context of a word through lexical co-occurrence networks. The implementation was trained and evaluated on a large corpus, and results show that the inclusion of second-order co-occurrence relations improves the performance of our implemented lexical choice program. | |
| dc.description | 3 pages, LaTeX2e, 1 ps figure, uses mathptm.sty, colacl.sty, psfig.sty | |
| dc.identifier | https://arxiv.org/abs/cs/9811009 | |
| dc.identifier | http://arxiv.org/abs/cs/9811009 | |
| dc.identifier | Proceedings of ACL-EACL '97, student session | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/33081 | |
| dc.subject | Computation and Language | |
| dc.subject | I.2.7 | |
| dc.title | Choosing the Word Most Typical in Context Using a Lexical Co-occurrence Network | |
| dc.type | text |