Numerical methods for retrieval and adaptation in Nagao’s EBMT model

Kun He, Tianjing Zhao, Yves Lepage

研究成果: Conference contribution

抜粋

We build an example-based machine translation system. It is an instance of case-based reasoning for machine translation. We introduce numerical methods instead of symbolic methods in two steps: retrieval and adaptation. For retrieval, we test three different approaches to define similarity between sentences. For adaptation, we use neural networks to solve analogies between sentences across languages. Oracle experiments allow to identify the best retrieval technique and to estimate the possibilities of such an approach. The system could place itself between a statistical and a neural machine translation systems on a task with not so large data.

元の言語English
ホスト出版物のタイトル2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018
出版者Institute of Electrical and Electronics Engineers Inc.
ページ195-200
ページ数6
ISBN(電子版)9781728101354
DOI
出版物ステータスPublished - 2019 1 17
イベント10th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018 - Yogyakarta, Indonesia
継続期間: 2018 10 272018 10 28

出版物シリーズ

名前2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018

Conference

Conference10th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018
Indonesia
Yogyakarta
期間18/10/2718/10/28

    フィンガープリント

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition
  • Library and Information Sciences
  • Artificial Intelligence
  • Information Systems

これを引用

He, K., Zhao, T., & Lepage, Y. (2019). Numerical methods for retrieval and adaptation in Nagao’s EBMT model. : 2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018 (pp. 195-200). [8618226] (2018 International Conference on Advanced Computer Science and Information Systems, ICACSIS 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICACSIS.2018.8618226