A Tensor-based Factorization Model of Semantic Compositionality - Université Toulouse 1 Capitole Accéder directement au contenu
Communication Dans Un Congrès Année : 2013

A Tensor-based Factorization Model of Semantic Compositionality

Résumé

In this paper, we present a novel method for the computation of compositionality within a distributional framework. The key idea is that compositionality is modeled as a multi-way interaction between latent factors, which are automatically constructed from corpus data. We use our method to model the composition of subject verb object triples. The method consists of two steps. First, we compute a latent factor model for nouns from standard co-occurrence data. Next, the latent factors are used to induce a latent model of three-way subject verb object interactions. Our model has been evaluated on a similarity task for transitive phrases, in which it exceeds the state of the art.
Fichier principal
Vignette du fichier
naaclhlt2013.pdf (140.8 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-00997334 , version 1 (30-05-2014)

Identifiants

  • HAL Id : hal-00997334 , version 1

Citer

Tim van de Cruys, Thierry Poibeau, Anna Korhonen. A Tensor-based Factorization Model of Semantic Compositionality. Conference of the North American Chapter of the Association of Computational Linguistics (HTL-NAACL), Jun 2013, Atlanta, United States. pp.1142-1151. ⟨hal-00997334⟩
467 Consultations
519 Téléchargements

Partager

Gmail Facebook X LinkedIn More