Fine-grained tree-to-string translation rule extraction

  • Authors:

  • Xianchao Wu;Takuya Matsuzaki;Jun'ichi Tsujii

  • Affiliations:

  • The University of Tokyo, Bunkyo-ku, Tokyo, Japan;The University of Tokyo, Bunkyo-ku, Tokyo, Japan;The University of Tokyo, Bunkyo-ku, Tokyo, Japan and University of Manchester and National Centre for Text Mining (NaCTeM), Manchester, UK

  • Venue:
  • ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
  • Year:
  • 2010

Quantified Score

Hi-index 0.00

Visualization

Abstract

Tree-to-string translation rules are widely used in linguistically syntax-based statistical machine translation systems. In this paper, we propose to use deep syntactic information for obtaining fine-grained translation rules. A head-driven phrase structure grammar (HPSG) parser is used to obtain the deep syntactic information, which includes a fine-grained description of the syntactic property and a semantic representation of a sentence. We extract fine-grained rules from aligned HPSG tree/forest-string pairs and use them in our tree-to-string and string-to-tree systems. Extensive experiments on large-scale bidirectional Japanese-English translations testified the effectiveness of our approach.