Measuring Thematic Fit with Distributional Feature Overlap - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Measuring Thematic Fit with Distributional Feature Overlap

Résumé

In this paper, we introduce a new distri-butional method for modeling predicate-argument thematic fit judgments. We use a syntax-based DSM to build a prototyp-ical representation of verb-specific roles: for every verb, we extract the most salient second order contexts for each of its roles (i.e. the most salient dimensions of typical role fillers), and then we compute thematic fit as a weighted overlap between the top features of candidate fillers and role prototypes. Our experiments show that our method consistently outperforms a baseline re-implementing a state-of-the-art system, and achieves better or comparable results to those reported in the literature for the other unsupervised systems. Moreover, it provides an explicit representation of the features characterizing verb-specific semantic roles.
Fichier principal
Vignette du fichier
emnlp-measuring-thematic.pdf (395.15 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01588246 , version 1 (15-09-2017)

Identifiants

  • HAL Id : hal-01588246 , version 1

Citer

Enrico Santus, Emmanuele Chersoni, Alessandro Lenci, Philippe Blache. Measuring Thematic Fit with Distributional Feature Overlap. Proceedings of the Conference on Empirical Methods for Natural Language Processing 2017, Sep 2017, Copenaghen, Denmark. ⟨hal-01588246⟩
117 Consultations
122 Téléchargements

Partager

Gmail Facebook X LinkedIn More