Modeling Violations of Selectional Restrictions with Distributional Semantics - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2018

Modeling Violations of Selectional Restrictions with Distributional Semantics

Résumé

Distributional Semantic Models have been successfully used for modeling selectional preferences in a variety of scenarios, since distributional similarity naturally provides an estimate of the degree to which an argument satisfies the requirement of a given predicate. However, we argue that the performance of such models on rare verb-argument combinations has received relatively little attention: it is not clear whether they are able to distinguish the combinations that are simply atypical, or implausible, from the semantically anomalous ones, and in particular, they have never been tested on the task of modeling their differences in processing complexity. In this paper, we compare two different models of thematic fit by testing their ability of identifying violations of selectional restrictions in two datasets from the experimental studies.
Fichier principal
Vignette du fichier
modeling-violations-selectional (1).pdf (234.97 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01838229 , version 1 (13-07-2018)

Identifiants

  • HAL Id : hal-01838229 , version 1

Citer

Emmanuele Chersoni, Adrià Torrens Urrutia, Philippe Blache, Alessandro Lenci. Modeling Violations of Selectional Restrictions with Distributional Semantics. COLING Workshop on Linguistic Complexity and Natural Language Processing, Aug 2018, Santa Fe, United States. ⟨hal-01838229⟩
103 Consultations
115 Téléchargements

Partager

Gmail Facebook X LinkedIn More