Composition in Distributional Models of Semantics
Article first published online: 3 NOV 2010
Copyright © 2010 Cognitive Science Society, Inc.
Volume 34, Issue 8, pages 1388–1429, November 2010
How to Cite
Mitchell, J. and Lapata, M. (2010), Composition in Distributional Models of Semantics. Cognitive Science, 34: 1388–1429. doi: 10.1111/j.1551-6709.2010.01106.x
- Issue published online: 3 NOV 2010
- Article first published online: 3 NOV 2010
- Received 6 May 2009; received in revised form 22 March 2010; accepted 25 March 2010
- Distributional models;
- Semantic spaces;
- Meaning representations;
- Phrase similarity
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.