Composition in Distributional Models of Semantics

Jeff Mitchell, Mirella Lapata

Research output: Contribution to journalArticlepeer-review

Abstract / Description of output

Vector-based models of word meaning have become increasingly popular in cognitive science. The appeal of these models lies in their ability to represent meaning simply by using distributional information under the assumption that words occurring within similar contexts are semantically similar. Despite their widespread use, vector-based models are typically directed at representing words in isolation, and methods for constructing representations for phrases or sentences have received little attention in the literature. This is in marked contrast to experimental evidence (e.g., in sentential priming) suggesting that semantic similarity is more complex than simply a relation between isolated words. This article proposes a framework for representing the meaning of word combinations in vector space. Central to our approach is vector composition, which we operationalize in terms of additive and multiplicative functions. Under this framework, we introduce a wide range of composition models that we evaluate empirically on a phrase similarity task.
Original languageEnglish
Pages (from-to)1388-1429
Number of pages42
JournalCognitive Science: A Multidisciplinary Journal
Volume34
Issue number8
DOIs
Publication statusPublished - Nov 2010

Keywords / Materials (for Non-textual outputs)

  • Distributional models
  • Semantic spaces
  • Compositionality
  • Meaning representations
  • Connectionism
  • Phrase similarity

Fingerprint

Dive into the research topics of 'Composition in Distributional Models of Semantics'. Together they form a unique fingerprint.

Cite this