Improving sampling-based alignment by investigating the distribution of N-grams in phrase translation tables

Juan Luo, Adrien Lardilleux, Yves Lepage

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

This paper describes an approach to improve the performance of sampling-based multilingual alignment on translation tasks by investigating the distribution of n-grams in the translation tables. This approach consists in enforcing the alignment of n-grams. The quality of phrase translation tables output by this approach and that of MGIZA++ is compared in statistical machine translation tasks. Significant improvements for this approach are reported. In addition, merging translation tables is shown to outperform state-of-the-art techniques.

本文言語English
ホスト出版物のタイトルPACLIC 25 - Proceedings of the 25th Pacific Asia Conference on Language, Information and Computation
ページ150-159
ページ数10
出版ステータスPublished - 2011 12 1
イベント25th Pacific Asia Conference on Language, Information and Computation, PACLIC 25 - , Singapore
継続期間: 2011 12 162011 12 18

出版物シリーズ

名前PACLIC 25 - Proceedings of the 25th Pacific Asia Conference on Language, Information and Computation

Conference

Conference25th Pacific Asia Conference on Language, Information and Computation, PACLIC 25
CountrySingapore
Period11/12/1611/12/18

ASJC Scopus subject areas

  • Language and Linguistics
  • Computer Science (miscellaneous)

フィンガープリント 「Improving sampling-based alignment by investigating the distribution of N-grams in phrase translation tables」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル