51
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: not found

      Composition in distributional models of semantics.

      1 ,
      Cognitive science

      Read this article at

      ScienceOpenPublisherPubMed
      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          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.

          Related collections

          Author and article information

          Journal
          Cogn Sci
          Cognitive science
          1551-6709
          0364-0213
          Nov 2010
          : 34
          : 8
          Affiliations
          [1 ] School of Informatics, University of Edinburgh.
          Article
          10.1111/j.1551-6709.2010.01106.x
          21564253
          2239b64e-57f7-4199-b469-27caf07abc40
          Copyright © 2010 Cognitive Science Society, Inc.
          History

          Comments

          Comment on this article