RefGen: Identifying Reference Chains to Detect Topics - HAL-SHS - Sciences de l'Homme et de la Société Accéder directement au contenu
Chapitre D'ouvrage Année : 2011

RefGen: Identifying Reference Chains to Detect Topics

Laurence Longo
Amalia Todirascu

Résumé

In this paper, we present RefGen, the main module of a topic detection system used to improve a search engine by topic indexing. RefGen identifies reference chains and it uses genre specific properties of reference chains and (Ariel 1990)’s accessibility theory. RefGen checks several strong and weak constraints (lexical, morphosyntactic and semantic filters) to automatically identify coreference relations between referential expressions. We present the first results obtained by RefGen from a public reports corpus.

Domaines

Linguistique

Dates et versions

halshs-01225270 , version 1 (05-11-2015)

Identifiants

Citer

Laurence Longo, Amalia Todirascu. RefGen: Identifying Reference Chains to Detect Topics. Advances in Distributed Agent-Based Retrieval Tools, 361, , pp.27-40, 2011, Studies in Computational Intelligence, 978-3-642-21383-0. ⟨10.1007/978-3-642-21384-7_3⟩. ⟨halshs-01225270⟩

Collections

SITE-ALSACE
93 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More