Composition in Distributional Models of Semantics
- 3 November 2010
- journal article
- Published by Wiley in Cognitive Science
- Vol. 34 (8), 1388-1429
- https://doi.org/10.1111/j.1551-6709.2010.01106.x
Abstract
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.Keywords
This publication has 74 references indexed in Scilit:
- Data from eye-tracking corpora as evidence for theories of syntactic processing complexityCognition, 2008
- Dependency-Based Construction of Semantic Space ModelsComputational Linguistics, 2007
- A Probabilistic Account of Logical MetonymyComputational Linguistics, 2003
- Integrating structure and meaning: a distributed model of analogical mappingCognitive Science, 2001
- PredicationCognitive Science, 2001
- The measurement of textual coherence with latent semantic analysisDiscourse Processes, 1998
- Similarity and property effects in inductive reasoning.Journal of Experimental Psychology: Learning, Memory, and Cognition, 1994
- Indexing by latent semantic analysisJournal of the American Society for Information Science, 1990
- This is like that: The use of earlier problems and the separation of similarity effects.Journal of Experimental Psychology: Learning, Memory, and Cognition, 1987
- Robust effects of syntactic structure on visual word processingMemory & Cognition, 1986