Context-Sensitive Measurement of Word Distance by Adaptive Scaling of a Semantic Space

@article{Kozima1995ContextSensitiveMO,
  title={Context-Sensitive Measurement of Word Distance by Adaptive Scaling of a Semantic Space},
  author={Hideki Kozima and Akira Ito},
  journal={CoRR},
  year={1995},
  volume={cmp-lg/9601007}
}
The paper proposes a computationally feasible method for measuring contextsensitive semantic distance between words. The distance is computed by adaptive scaling of a semantic space. In the semantic space, each word in the vocabulary V is represented by a multidimensional vector which is obtained from an English dictionary through a principal component analysis. Given a word set C which specifies a context for measuring word distance, each dimension of the semantic space is scaled up or down… CONTINUE READING
Highly Cited
This paper has 20 citations. REVIEW CITATIONS

References

Publications referenced by this paper.
Showing 1-10 of 14 references

Cooccurrence vectors from corpora vs. distance vectors from dictionaries

  • Niwa, Nitta 94 Y. Niwa, Y. Nitta
  • Proceedings of the 15th International Conference…
  • 1994

Classbased n-gram models of natural language

  • Brown
  • Computational Linguistics,
  • 1992

Tell Me a Story: A New Look at Real and Artificial Memory

  • R. C. Schank
  • 1990
1 Excerpt

Rhetorical structure theory: a theory of text organization

  • W. C. Mann, S. A. Thompson
  • Technical Report of Information Science Institute…
  • 1987
2 Excerpts

Similar Papers

Loading similar papers…