How useful are similarity word lists for indirect anaphora resolution?

Fiche du document

Date

2005

Discipline
Type de document
Périmètre
Langue
Identifiants
Collection

Archives ouvertes

Licence

info:eu-repo/semantics/OpenAccess



Sujets proches En

Frenchmen (French people)

Citer ce document

Susanne Salmon-Alt et al., « How useful are similarity word lists for indirect anaphora resolution? », HAL-SHS : linguistique, ID : 10670/1.i10vyr


Métriques


Partage / Export

Résumé 0

This work tests the use of word similarity lists for anaphora resolution in Portuguese and French corpora. We applied an automaticlexical acquisition technique over parsed texts to identify semantically similar words. We then made use of this lexical knowledge toresolve coreferential definite descriptions where the head noun of the anaphor is different from the head noun of its antecedent, whichwe call indirect anaphora. We compare the results in both languages with a baseline algorithm. Our proposed technique achieved an Fmeasureof 0.26 for Portuguese and 0.09 for French.

document thumbnail

Par les mêmes auteurs

Sur les mêmes sujets

Sur les mêmes disciplines

Exporter en