A Survey of Domain Adaptation for Machine Translation

• Chu Chenhui

  Institute for Datability Science, Osaka University

• Wang Rui

  National Institute of Information and Communications Technology

Abstract

Neural machine translation (NMT) is a deep learning based approach for machine translation, which outperforms traditional statistical machine translation (SMT) and yields the state-of-the-art translation performance in scenarios where large-scale parallel corpora are available. Although a high-quality and domain-specific translation is crucial in the real world, domain-specific corpora are usually scarce or nonexistent, and thus vanilla NMT performs poorly in such scenarios. Domain adaptation that leverages both out-of-domain parallel corpora as well as monolingual corpora for in-domain translation, is very important for domain-specific translation. In this paper, we give a comprehensive survey of the state-of-the-art domain adaptation techniques for MT. Because of the current dominance of NMT in MT research, we give a brief review of domain adaptation for SMT, but put most of our effort into the survey of domain adaptation for NMT. We hope that this paper will be both a starting point and a source of new ideas for researchers and engineers who are interested in domain adaptation for MT.

Journal

• Journal of Information Processing

  Journal of Information Processing 28 (0), 413-426, 2020

  Information Processing Society of Japan

Keywords

• neural machine translation
• domain adaptation
• survey

Details

• CRID: 1390003825205780480
• NII Article ID: 130007887723
• DOI: 10.2197/ipsjjip.28.413
• ISSN: 18826652
• Web Site: https://www.jstage.jst.go.jp/article/ipsjjip/28/0/28_413/_pdf
• Text Lang: en
• Data Source:
  • JaLC
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed