Dealing with Metonymic Readings of Named Entities

Simple item page
dc.creatorPoibeau, Thierry
dc.date2006-07-11
dc.date.accessioned2026-07-07T08:47:46Z
dc.date.available2026-07-07T08:47:46Z
dc.descriptionThe aim of this paper is to propose a method for tagging named entities (NE), using natural language processing techniques. Beyond their literal meaning, named entities are frequently subject to metonymy. We show the limits of current NE type hierarchies and detail a new proposal aiming at dynamically capturing the semantics of entities in context. This model can analyze complex linguistic phenomena like metonymy, which are known to be difficult for natural language processing but crucial for most applications. We present an implementation and some test using the French ESTER corpus and give significant results.
dc.identifierhttps://arxiv.org/abs/cs/0607052
dc.identifierhttp://arxiv.org/abs/cs/0607052
dc.identifierDans Actes de The 28th Annual Conference of the Cognitive Science Society (CogSci 2006) - The 28th Annual Conference of the Cognitive Science Society (CogSci 2006), Vancouver : Canada (2006)
dc.identifier.urihttp://salesiana.dossiersoluciones.com/handle/123456789/143716
dc.subjectArtificial Intelligence
dc.subjectComputation and Language
dc.titleDealing with Metonymic Readings of Named Entities
dc.typetext

Files

Collections

arXiv