Syntactic Skeleton-Based Translation

Authors

  • Tong Xiao Northeastern University
  • Jingbo Zhu Northeastern University
  • Chunliang Zhang Northeastern University
  • Tongran Liu Institute of Psychology (CAS)

DOI:

https://doi.org/10.1609/aaai.v30i1.10343

Keywords:

Statistical Machine Translation, Syntax-Based Model

Abstract

In this paper we propose an approach to modeling syntactically-motivated skeletal structure of source sentence for machine translation. This model allows for application of high-level syntactic transfer rules and low-level non-syntactic rules. It thus involves fully syntactic, non-syntactic, and partially syntactic derivations via a single grammar and decoding paradigm. On large-scale Chinese-English and English-Chinese translation tasks, we obtain an average improvement of +0.9 BLEU across the newswire and web genres.

AAAI 2016 Proceedings Cover

Downloads

Published

2016-03-05

How to Cite

Xiao, T., Zhu, J., Zhang, C., & Liu, T. (2016). Syntactic Skeleton-Based Translation. Proceedings of the AAAI Conference on Artificial Intelligence, 30(1). https://doi.org/10.1609/aaai.v30i1.10343

Issue

Vol. 30 No. 1 (2016): Thirtieth AAAI Conference on Artificial Intelligence

Section

Technical Papers: NLP and Machine Learning