A Reordering Model for Phrase-Based Machine Translation

  • Authors:
  • Vinh Nguyen;Thai Phuong Nguyen;Akira Shimazu;Minh Nguyen

  • Affiliations:
  • Japan Advanced Institute of Science and Technology, Japan 923-1292;Japan Advanced Institute of Science and Technology, Japan 923-1292;Japan Advanced Institute of Science and Technology, Japan 923-1292;Japan Advanced Institute of Science and Technology, Japan 923-1292

  • Venue:
  • GoTAL '08 Proceedings of the 6th international conference on Advances in Natural Language Processing
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a new method for reordering in phrase based statistical machine translation (PBSMT). Our method is based on previous chunk-level reordering methods for PBSMT. Our method is a global reordering. First, we parse the source language sentence to a chunk tree, according to the method developed by [1]. Second, we apply a series of transformation rules, which are learnt automatically from the parallel corpus to the chunk tree over chunk level. Finally, we solve phenomena for the overlapping of phrases and chunks, and integrate a global reordering model directly in a decoder as a graph of phrases. The experimental results with English-Vietnamese and English-French pairs show that our method outperforms the baseline PBSMT in both accuracy and speed.