K-vec: a new approach for aligning parallel texts

  • Authors:
  • Pascale Fung;Kenneth Ward Church

  • Affiliations:
  • Columbia University, New York, NY;AT&T Bell Laboratories, Murray Hill, NJ

  • Venue:
  • COLING '94 Proceedings of the 15th conference on Computational linguistics - Volume 2
  • Year:
  • 1994

Quantified Score

Hi-index 0.00

Visualization

Abstract

Various methods have been proposed for aligning texts in two or more languages such as the Canadian Parliamentary Debates (Hansards). Some of these methods generate a bilingual lexicon as a by-product. We present an alternative alignment strategy which we call K-vec, that starts by estimating the lexicon. For example, it discovers that the English word fisheries is similar to the French pêches by noting that the distribution of fisheries in the English text is similar to the distribution of pê'ches in the French. K-vec does not depend on sentence boundaries.