OATAO - Open Archive Toulouse Archive Ouverte Open Access Week

A Tensor-based Factorization Model of Semantic Compositionality

Van de Cruys, Tim and Poibeau, Thierry and Korhonen, Anna A Tensor-based Factorization Model of Semantic Compositionality. (2013) In: Conference of the North American Chapter of the Association for Computational Linguistics : Human Language Technologies (NAACL-HLT 2013), 9 June 2013 - 15 June 2013 (Atlanta, GA, United States).

(Document in English)

PDF (Author's version) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader

Official URL: http://www.aclweb.org/anthology/N13-1134


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.

Item Type:Conference or Workshop Item (Paper)
Audience (conference):International conference proceedings
Uncontrolled Keywords:
Institution:French research institutions > Centre National de la Recherche Scientifique - CNRS (FRANCE)
Université de Toulouse > Institut National Polytechnique de Toulouse - Toulouse INP (FRANCE)
Other partners > University of Cambridge (UNITED KINGDOM)
Université de Toulouse > Université Toulouse III - Paul Sabatier - UT3 (FRANCE)
Université de Toulouse > Université Toulouse - Jean Jaurès - UT2J (FRANCE)
Université de Toulouse > Université Toulouse 1 Capitole - UT1 (FRANCE)
Other partners > Ecole Normale Supérieure de Paris - ENS Paris (FRANCE)
Laboratory name:
Deposited On:27 Oct 2015 14:49

Repository Staff Only: item control page