How useful are similarity word lists for indirect anaphora resolution? - HAL Accéder directement au contenu
Communication dans un congrès Actes : 5th International Conference on Discourse Anaphora and Anaphor Resolution, Furnas, Portugal (September 23 - 24, 2004). Année : 2005

How useful are similarity word lists for indirect anaphora resolution?

Renata Vieira
  • Fonction : Auteur
Caroline Gasperin
  • Fonction : Auteur

Résumé

This work tests the use of word similarity lists for anaphora resolution in Portuguese and French corpora. We applied an automatic
lexical acquisition technique over parsed texts to identify semantically similar words. We then made use of this lexical knowledge to
resolve coreferential definite descriptions where the head noun of the anaphor is different from the head noun of its antecedent, which
we call indirect anaphora. We compare the results in both languages with a baseline algorithm. Our proposed technique achieved an Fmeasure
of 0.26 for Portuguese and 0.09 for French.
Fichier principal
Vignette du fichier
daarc-5-1_1_.pdf ( 70.08 Ko ) Télécharger
Loading...

Dates et versions

halshs-00005020, version 1 (17-10-2005)

Identifiants

  • HAL Id : halshs-00005020 , version 1

Citer

Susanne Salmon-Alt, Renata Vieira, Caroline Gasperin. How useful are similarity word lists for indirect anaphora resolution?. Actes : 5th International Conference on Discourse Anaphora and Anaphor Resolution, Furnas, Portugal (September 23 - 24, 2004)., 2005. ⟨halshs-00005020⟩
142 Consultations
141 Téléchargements
Dernière date de mise à jour le 20/04/2024
comment ces indicateurs sont-ils produits

Partager

Gmail Facebook Twitter LinkedIn Plus