Choosing the Word Most Typical in Context Using a Lexical Co-occurrence Network

dc.creatorEdmonds, Philip
dc.date1998-11-02
dc.date.accessioned2026-07-07T03:23:47Z
dc.date.available2026-07-07T03:23:47Z
dc.descriptionThis 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.description3 pages, LaTeX2e, 1 ps figure, uses mathptm.sty, colacl.sty, psfig.sty
dc.identifierhttps://arxiv.org/abs/cs/9811009
dc.identifierhttp://arxiv.org/abs/cs/9811009
dc.identifierProceedings of ACL-EACL '97, student session
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/33081
dc.subjectComputation and Language
dc.subjectI.2.7
dc.titleChoosing the Word Most Typical in Context Using a Lexical Co-occurrence Network
dc.typetext

Files

Collections