Forest-based translation rule extraction

  • Authors:

  • Haitao Mi;Liang Huang

  • Affiliations:

  • Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China;University of Pennsylvania, Philadelphia, PA and Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China

  • Venue:
  • EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

Translation rule extraction is a fundamental problem in machine translation, especially for linguistically syntax-based systems that need parse trees from either or both sides of the bi-text. The current dominant practice only uses 1-best trees, which adversely affects the rule set quality due to parsing errors. So we propose a novel approach which extracts rules from a packed forest that compactly encodes exponentially many parses. Experiments show that this method improves translation quality by over 1 BLEU point on a state-of-the-art tree-to-string system, and is 0.5 points better than (and twice as fast as) extracting on 30-best parses. When combined with our previous work on forest-based decoding, it achieves a 2.5 BLEU points improvement over the base-line, and even outperforms the hierarchical system of Hiero by 0.7 points.