A Generalisation of Lexical Functions for Composition in Distributional Semantics

Antoine Bride (1) , Tim van de Cruys (1) , Nicholas Asher (1, 2)

1 IRIT-MELODI - MEthodes et ingénierie des Langues, des Ontologies et du DIscours
2 CNRS - Centre National de la Recherche Scientifique

Over the last two decades, numerous algorithms have been developed that successfully capture something of the semanticsof single words by looking at their distribution in text and comparing these distributions in a vector space model. However, it is not straightforward to construct meaning representations beyond the levelof individual words–i.e. the combination of words into larger units – using dis-tributional methods. Our contribution is twofold. First of all, we carry out a large-scale evaluation, comparing different composition methods within the distributional framework for the cases of both adjective-noun and noun-noun composition, makinguse of a newly developed dataset. Secondly, we propose a novel method focomposition, which generalises the approach by Baroni and Zamparelli (2010). The performance of our novel method is also evaluated on our new dataset andproves competitive with the best methods.

Mots clés: Composition in distributional semantics

Domaines: Informatique et langage [cs.CL]

Antoine Bride, Tim van de Cruys, Nicholas Asher. A Generalisation of Lexical Functions for Composition in Distributional Semantics. 53rd Annual Meeting of the Association for Computational Linguistics (ACL 2015), Jul 2015, Beijing, China. pp.281-291. ⟨hal-02355284⟩