Better filtration and augmentation for hierarchical phrase-based translation rules

  • Authors:
  • Zhiyang Wang;Yajuan Lü;Qun Liu;Young-Sook Hwang

  • Affiliations:
  • Chinese Academy of Sciences, Beijing, China;Chinese Academy of Sciences, Beijing, China;Chinese Academy of Sciences, Beijing, China;HILab Convergence Technology Center, Jung-gu, Seoul, Korea

  • Venue:
  • ACLShort '10 Proceedings of the ACL 2010 Conference Short Papers
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a novel filtration criterion to restrict the rule extraction for the hierarchical phrase-based translation model, where a bilingual but relaxed well-formed dependency restriction is used to filter out bad rules. Furthermore, a new feature which describes the regularity that the source/target dependency edge triggers the target/source word is also proposed. Experimental results show that, the new criteria weeds out about 40% rules while with translation performance improvement, and the new feature brings another improvement to the baseline system, especially on larger corpus.