Log-linear models for word alignment

  • Authors:
  • Yang Liu;Qun Liu;Shouxun Lin

  • Affiliations:
  • Institute of Computing Technology, Haidian District, Beijing, China;Institute of Computing Technology, Haidian District, Beijing, China;Institute of Computing Technology, Haidian District, Beijing, China

  • Venue:
  • ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

We present a framework for word alignment based on log-linear models. All knowledge sources are treated as feature functions, which depend on the source language sentence, the target language sentence and possible additional variables. Log-linear models allow statistical alignment models to be easily extended by incorporating syntactic information. In this paper, we use IBM Model 3 alignment probabilities, POS correspondence, and bilingual dictionary coverage as features. Our experiments show that log-linear models significantly outperform IBM translation models.