Combining corpus-based pattern distributions with lexical signatures for PP attachment ambiguity resolution - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2005

Combining corpus-based pattern distributions with lexical signatures for PP attachment ambiguity resolution

Résumé

In this paper, we propose a method combining unsupervised learning of lexical frequencies with semantic information aiming at improving PP attachment ambiguity resolution. Using the output of a robust parser, i.e. the set of all possible attachments for a given sentence, we query the Web and obtain statistical information about the frequencies of the attachments distributions as well as lexical signatures of the terms on the patterns. All this information is used to weight the dependencies yielded by the parser.
Fichier principal
Vignette du fichier
GalaLafourcade_SNLP05.pdf (79.28 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03198432 , version 1 (14-04-2021)

Identifiants

  • HAL Id : hal-03198432 , version 1

Citer

Núria Gala, Mathieu Lafourcade. Combining corpus-based pattern distributions with lexical signatures for PP attachment ambiguity resolution. 6th Symposium on Natural Language Processing (SNLP 2005), Dec 2005, Chiang Rai, Thailand. ⟨hal-03198432⟩
59 Consultations
21 Téléchargements

Partager

Gmail Facebook X LinkedIn More