A Cognitive Approach to Word Sense Disambiguation

  • Sudakshina Dutta
  • Anupam Basu
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7181)

Abstract

An unsupervised, knowledge-based, parametric approach to Word Sense Disambiguation is proposed based on the well-known cognitive architecture ACT-R. In this work, the target word is disambiguated based on surrounding context words using an accumulator model of memory search and it is realized by incorporating RACE/A with ACT-R 6.0. In this process, a spreading activation network is built following the strategies of Tsatsaronis et al. proposed in [5] using the chunks and their relations in the declarative memory system of ACT-R and the lexical representation has been achieved by integrating WordNet with the cognitive architecture. The resulting Word Sense Disambiguation system is evaluated using the test data set from English Lexical Sample task of Senseval-2 and overall accuracy of the proposed algorithm is 44.74% which outperforms all the participating Word Sense Disambiguation Systems.

Keywords

WSD Word Sense Disambiguation RACE/A Retrieval by ACcumulating Evidence in an Architecture ACT-R Adaptive Control of Thought-Rational SAN Spreading Activation Network 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Collins, A.M., Loftus, E.F.: A spreading activation theory of semantic processing. Psychological Review 82(6), 407–428 (1975)CrossRefGoogle Scholar
  2. 2.
    Emond, B.: WN-LEXICAL: An ACT-R module built from the WordNet Lexical database. In: Proc. of the Seventh International Conference on Cognitive Modelling, Trieste, Italy, pp. 359–360 (2006)Google Scholar
  3. 3.
    Melamed, D., Resnik, P.: Melamed and Resnik’s Proposal for Senseval scoring (October 8, 2011), http://www.cse.unt.edu/~rada/senseval/senseval3/scoring/scorescheme.txt
  4. 4.
    Meyer, D.E., Schvaneveldt, R.E.: Facilitation in recognizing pairs of words: Evidence of a dependence between retrieval operations. Journal of Experimental Psychology 90(2), 227–234 (1971)CrossRefGoogle Scholar
  5. 5.
    Tsatsaronis, G., Vazirgiannis, M., Androutsopoulos, I.: Word Sense Disambiguation with Spreading Activation Networks Generated from Thesauri. In: Proc. of IJCAI 2007, pp. 1725–1730 (2007)Google Scholar
  6. 6.
    Miller, G.A., Beckwith, R., Fellbaum, C., Gross, D., Miller, K.: WordNet: An online lexical database. Int. J. Lexicograph 3(4), 235–244 (1990)CrossRefGoogle Scholar
  7. 7.
    Berger, H., Dittenbach, M., Markl, D.: An adaptive information retrieval system based on associative networks. In: Proc. of the 1st Asia-Pacific Conference on Conceptual Modelling, Dunedin, New Zealand, pp. 27–36 (2004)Google Scholar
  8. 8.
    Anderson, J.R.: Language, Memory, and Thought. Lawrence Erlbaum and Associates, Hillsdale (1976)Google Scholar
  9. 9.
    Anderson, J.R.: A Spreading Activation Theory of Memory. Journal of Verbal Learning and Verbal Behavior 22(3), 261–295 (1983)CrossRefGoogle Scholar
  10. 10.
    Anderson, J.R., Lebiere, C.: The atomic components of thought. Erlbaum, Mahwah (1998)Google Scholar
  11. 11.
    Anderson, J., Bothell, D.: Tutorials and Reference Manual of ACT-R (2011), http://act-r.psy.cmu.edu/actr6/
  12. 12.
    Veronis, J., Ide, N.M.: Word sense disambiguation with very large neural networks extracted from machine readable dictionaries. In: Proc. of COLING 1990, Helsinki, Finland, pp. 389–394 (1990)Google Scholar
  13. 13.
    Van Maanen, L., Van Rijn, H.: RACE for retrieval: Competitive effects in memory retrieval. In: Proc. of 12th Annual ACT-R Workshop, 12th edn., Triests (2005)Google Scholar
  14. 14.
    Van Maanen, L.: Context effects on memory retrieval: Theory and applications. PhD thesis, University of Groningen, Groningen (2009)Google Scholar
  15. 15.
    Lesk, M.: Automatic sense disambiguation using machine readable dictionaries: How to tell a pine cone from a ice cream cone. In: Proc. of SIGDOC (1986)Google Scholar
  16. 16.
    Ross Quillian, M.: A design for an understanding machine. In: Communication Presented at the Colloquium Semantic Problems in Natural Language. Kings College, Cambridge University, Cambridge, United Kingdom (1961)Google Scholar
  17. 17.
    Ross Quillian, M.: A semantic coding technique for mechanical English paraphrasing. Internal memorandum of the Mechanical translation Group. Research Laboratory of Electronics, M. I. T (August 1962)Google Scholar
  18. 18.
    Ross Quillian, M.: Word concepts: A theory and simulation of some basic semantic capabilities. The Journal of Behavioral Science 12, 410–430 (1967)CrossRefGoogle Scholar
  19. 19.
    Ross Quillian, M.: Semantic memory. In: Minsky, M. (ed.) Semantic Information Processing, pp. 227–270. MIT Press (1968)Google Scholar
  20. 20.
    Ross Quillian, M.: The teachable language comprehender: a simulation program and theory of language. Communication of ACM 12(8), 459–476 (1969)CrossRefGoogle Scholar
  21. 21.
    Byrne, M.D., Anderson, J.R., Qin, Y., Bothell, D., Douglass, S.A., Lebiere, C.: An Integrated theory of the mind. Psychological Review 111(4), 1036–1060 (2004)CrossRefGoogle Scholar
  22. 22.
    Usher, M., McClelland, J.L.: The time course of perceptual choice: The leaky, competing accumulator model. Psychological Review 108(3), 550–592 (2001)CrossRefGoogle Scholar
  23. 23.
    Ide, N., Veronis, J.: Word Sense Disambiguation: the state of the art. Computational Linguistics 24(1), 1–40 (1998)Google Scholar
  24. 24.
    Edmonds, P.: Designing a task for SENSEVAL-2 (2000), http://www.sle.sharp.co.uk/SENSEVAL2/archive/index.html
  25. 25.
    Edmonds, P., Cotton, S.: SENSEVAL-2:Overview. In: Proc. of The Second International Workshop on Evaluating Word Sense Disambiguation Systems (SENSEVAL-2), Toulouse, pp. 1–6 (2001)Google Scholar
  26. 26.
    Navigli, R.: Word sense disambiguation: a Survey. ACM Computing Surveys 41(2), 1–69 (2009)CrossRefGoogle Scholar
  27. 27.
    Ratcliff, R., Smith, P.L.: A comparison of sequential sampling models for two-choice reaction time. Psychological Review 111(2), 333–367 (2004)CrossRefGoogle Scholar
  28. 28.
    Satanjeev, B., Pedersen, T.: An Adapted Lesk Algorithm for Word Sense Disambiguation using WordNet. In: Proc. of the Third International Conference on Intelligent Text Processing and Computational Linguistics, Mexico City, pp. 136–145 (2002)Google Scholar
  29. 29.
    Chklovski, T., Mihalcea, R., Pedersen, T., Puradare, A.: The Senseval-3 multilingual English-Hindi lexical sample task. In: Proceedings of the 3rd International Workshop on the Evaluation of Systems for the Semantic Analysis of Text, Barcelona, Spain, p. 58 (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Sudakshina Dutta
    • 1
  • Anupam Basu
    • 1
  1. 1.Indian Institute of Technology KharagpurIndia

Personalised recommendations