Documents and Dependencies: an Exploration of Vector Space Models for Semantic Composition


Autoria(s): Fyshe, Alona; Talukdar, Partha; Murphy, Brian; Mitchell, Tom
Data(s)

2013

Resumo

In most previous research on distributional semantics, Vector Space Models (VSMs) of words are built either from topical information (e.g., documents in which a word is present), or from syntactic/semantic types of words (e.g., dependency parse links of a word in sentences), but not both. In this paper, we explore the utility of combining these two representations to build VSM for the task of semantic composition of adjective-noun phrases. Through extensive experiments on benchmark datasets, we find that even though a type-based VSM is effective for semantic composition, it is often outperformed by a VSM built using a combination of topic- and type-based statistics. We also introduce a new evaluation task wherein we predict the composed vector representation of a phrase from the brain activity of a human subject reading that phrase. We exploit a large syntactically parsed corpus of 16 billion tokens to build our VSMs, with vectors for both phrases and words, and make them publicly available.

Identificador

http://pure.qub.ac.uk/portal/en/publications/documents-and-dependencies-an-exploration-of-vector-space-models-for-semantic-composition(df7a2d5f-3fae-42bb-b0f0-1a34e97a2585).html

Idioma(s)

eng

Publicador

Association for Computational Linguistics

Direitos

info:eu-repo/semantics/closedAccess

Fonte

Fyshe , A , Talukdar , P , Murphy , B & Mitchell , T 2013 , Documents and Dependencies: an Exploration of Vector Space Models for Semantic Composition . in 17th Conference on Computational Natural Language Learning (CoNLL 2013) . Association for Computational Linguistics , pp. 84-93 .

Tipo

contributionToPeriodical