ABSTRACT
Vector space models of word meaning typically represent the meaning of a word as a vector computed by summing over all its corpus occurrences. Words close to this point in space can be assumed to be similar to it in meaning. But how far around this point does the region of similar meaning extend? In this paper we discuss two models that represent word meaning as regions in vector space. Both representations can be computed from traditional point representations in vector space. We find that both models perform at over 95% F-score on a token classification task.
- M. Connor and D. Roth. 2007. Context sensitive paraphrasing with a single unsupervised classifier. In Proceedings of ECML-07, Warsaw, Poland. Google ScholarDigital Library
- K. Erk and S. Pado. 2008. A structured vector space model for word meaning in context. In Proceedings of EMNLP-08, Hawaii. Google ScholarDigital Library
- K. Erk. 2009. Supporting inferences in semantic space: representing words as regions. In Proceedings of IWCS-8, Tilburg, Netherlands. Google ScholarDigital Library
- P. Gärdenfors. 2004. Conceptual spaces. MIT press, Cambridge, MA.Google Scholar
- M. Geffet and I. Dagan. 2005. The distributional inclusion hypotheses and lexical entailment. In Proceedings of ACL-05, Ann Arbor, MI. Google ScholarDigital Library
- J. Gorman and J. R. Curran. 2006. Scaling distributional similarity to large corpora. In Proceedings of ACL '06, Sydney. Google ScholarDigital Library
- J. A. Hampton. 1991. The combination of prototype concepts. In P. Schwanenflugel, editor, The psychology of word meanings. Lawrence Erlbaum Associates.Google Scholar
- P. Hanks. 2000. Do word meanings exist? Computers and the Humanities, 34(1--2):205--215(11).Google Scholar
- M. Jones and D. Mewhort. 2007. Representing word menaing and order information in a composite holographic lexicon. Psychological Review, 114:1--37.Google ScholarCross Ref
- A. Kilgarriff. 1997. I don't believe in word senses. Computers and the Humanities, 31(2):91--113.Google ScholarCross Ref
- W. Kintsch. 2001. Predication. Cognitive Science, 25:173--202.Google ScholarCross Ref
- T. Landauer and S. Dumais. 1997. A solution to Platos problem: the latent semantic analysis theory of acquisition, induction, and representation of knowledge. Psychological Review, 104(2):211--240.Google ScholarCross Ref
- D. Lin. 1993. Principle-based parsing without overgeneration. In Proceedings of ACL'93, Columbus, Ohio. Google ScholarDigital Library
- D. Lin. 1998. Automatic retrieval and clustering of similar words. In COLING-ACL98, Montreal, Canada. Google ScholarDigital Library
- W. Lowe and S. McDonald. 2000. The direct route: Mediated priming in semantic space. In Proceedings of the Cognitive Science Society.Google Scholar
- W. Lowe. 2001. Towards a theory of semantic space. In Proceedings of the Cognitive Science Society.Google Scholar
- K. Lund and C. Burgess. 1996. Producing high-dimensional semantic spaces from lexical co-occurrence. Behavior Research Methods, Instruments, and Computers, 28:203--208.Google ScholarCross Ref
- C. D. Manning, P. Raghavan, and H. Schütze. 2008. Introduction to Information Retrieval. Cambridge University Press. Google ScholarDigital Library
- D. McCarthy, R. Koeling, J. Weeds, and J. Carroll. 2004. Finding predominant senses in untagged text. In Proceedings of ACL'04, Barcelona, Spain. Google ScholarDigital Library
- S. McDonald and M. Ramscar. 2001. Testing the distributional hypothesis: The influence of context on judgements of semantic similarity. In Proceedings of the Cognitive Science Society.Google Scholar
- J. Mitchell and M. Lapata. 2008. Vector-based models of semantic composition. In Proceedings of ACL-08, Columbus, OH.Google Scholar
- G. L. Murphy. 2002. The Big Book of Concepts. MIT Press.Google Scholar
- R. M. Nosofsky. 1986. Attention, similarity, and the identification-categorization relationship. Journal of Experimental Psychology: General, 115:39--57.Google ScholarCross Ref
- S. Padó and M. Lapata. 2007. Dependency-based construction of semantic space models. Computational Linguistics, 33(2):161--199. Google ScholarDigital Library
- M. Sahlgren and J. Karlgren. 2005. Automatic bilingual lexicon acquisition using random indexing of parallel corpora. Journal of Natural Language Engineering, Special Issue on Parallel Texts, 11(3). Google ScholarDigital Library
- H. Schütze. 1998. Automatic word sense discrimination. Computational Linguistics, 24(1). Google ScholarDigital Library
- R. Shepard. 1987. Towards a universal law of generalization for psychological science. Science, 237(4820):1317--1323.Google ScholarCross Ref
- E. E. Smith, D. Osherson, L. J. Rips, and M. Keane. 1988. Combining prototypes: A selective modification model. Cognitive Science, 12(4):485--527.Google ScholarCross Ref
- P. Smolensky. 1990. Tensor product variable binding and the representation of symbolic structures in connectionist systems. Artificial Intelligence, 46:159--216. Google ScholarDigital Library
- R. Snow, D. Jurafsky, and A. Y. Ng. 2006. Semantic taxonomy induction from heterogenous evidence. In Proceedings of COLING/ACL'06. Google ScholarDigital Library
- I. Szpektor, I. Dagan, R. Bar-Haim, and J. Goldberger. 2008. Contextual preferences. In Proceedings of ACL-08, Columbus, OH.Google Scholar
- J. Weeds, D. Weir, and D. McCarthy. 2004. Characterising measures of lexical distributional similarity. In Proceedings of COLING-04, Geneva, Switzerland. Google ScholarDigital Library
Index Terms
- Representing words as regions in vector space
Recommendations
Representing words as lymphocytes
AAAI'14: Proceedings of the Twenty-Eighth AAAI Conference on Artificial IntelligenceSimilarity between words is becoming a generic problem for many applications of computational linguistics, and computing word similarities is determined by word representations. Inspired by the analogies between words and lymphocytes, a lymphocyte-style ...
Compositional approaches for representing relations between words
Identifying the relations that exist between words (or entities) is important for various natural language processing tasks such as, relational search, noun-modifier classification and analogy detection. A popular approach to represent the relations ...
Deep Learning Models for Representing Out-of-Vocabulary Words
Intelligent SystemsAbstractCommunication has become increasingly dynamic with the popularization of social networks and applications that allow people to express themselves and communicate instantly. In this scenario, distributed representation models have their quality ...
Comments