Improving Pivot Translation by Remembering the Pivot

DOI IR HANDLE Web Site Web Site 14 References Open Access
  • Miura Akiva
    Graduate School of Information Science, Nara Institute of Science and Technology
  • Neubig Graham
    Graduate School of Information Science, Nara Institute of Science and Technology Language Technologies Institute, Carnegie Mellon University
  • Sakti Sakriani
    Graduate School of Information Science, Nara Institute of Science and Technology
  • Toda Tomoki
    Information Technology Center, Nagoya University
  • Nakamura Satoshi
    Graduate School of Information Science, Nara Institute of Science and Technology

Bibliographic Information

Other Title
  • 中間言語情報を記憶するピボット翻訳手法
  • チュウカン ゲンゴ ジョウホウ オ キオクスル ピポット ホンヤク シュホウ
  • チュウカン ゲンゴ ジョウホウ オ キオク スル ピボット ホンヤク シュホウ

Search this article

Abstract

<p>In statistical machine translation, the pivot translation approach allows for translation of language pairs with little or no parallel data by introducing a third language for which data exists. In particular, the triangulation method, which translates by combining source-pivot and pivot-target translation models into a source-target model is known for its high translation accuracy. However, in the conventional triangulation method, information of pivot phrases is forgotten, and not used in the translation process. In this research, we propose a novel approach to remember the pivot phrases in the triangulation stage, and use a pivot language model as an additional information source at translation phase. Experimental results on the united nations parallel corpus showed significant improvements in all tested combinations of languages. </p>

Journal

References(14)*help

See more

Related Projects

See more

Keywords

Details 詳細情報について

Report a problem

Back to top