Is Structure Necessary for Modeling Argument Expectations in Distributional Semantics? - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2017

Is Structure Necessary for Modeling Argument Expectations in Distributional Semantics?

Résumé

Despite the number of NLP studies dedicated to thematic fit estimation, little attention has been paid to the related task of composing and updating verb argument expectations. The few exceptions have mostly modeled this phenomenon with structured distributional models, implicitly assuming a similarly structured representation of events. Recent experimental evidence, however, suggests that human processing system could also exploit an unstructured " bag-of-arguments " type of event representation to predict upcoming input. In this paper, we re-implement a traditional structured model and adapt it to compare the different hypotheses concerning the degree of structure in our event knowledge, evaluating their relative performance in the task of the argument expectations update.
Fichier principal
Vignette du fichier
structure-modeling-argument (1).pdf (231.91 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01610001 , version 1 (04-10-2017)

Identifiants

  • HAL Id : hal-01610001 , version 1

Citer

Emmanuele Chersoni, Enrico Santus, Philippe Blache, Alessandro Lenci. Is Structure Necessary for Modeling Argument Expectations in Distributional Semantics?. 12th International Conference on Computational Semantics (IWCS 2017), Sep 2017, Montpellier, France. ⟨hal-01610001⟩
80 Consultations
41 Téléchargements

Partager

Gmail Facebook X LinkedIn More