Hierarchical Statistical Machine Translation Using Sampling Based Alignment

スポンサーリンク

概要

• 論文の詳細を見る

• We propose an extension of the sampling-based alignment technique to implement the hierarchical phrases-based model. The proposed technique outputs a hierarchical phrase based rule table. It is learned from a bi-text without any syntactic information or any linguistic commitment. We expect the following advantages from our rule tables: 1. better reordering, 2. better translation of discontinuous phrases.

• 2014-01-30

著者

• Yves Lepage

  IPS, Waseda University

• Tongxu Liu

  IPS, Waseda University

関連論文

• Modifying Existing Analogy-based N-gram Language Model
• Hierarchical Statistical Machine Translation Using Sampling Based Alignment

スポンサーリンク