A Comprehensive Empirical Comparison of Domain Adaptation Methods for Neural Machine Translation

• Item type: Journal(1)
• 公開日: 2018-07-15
• タイトル: A Comprehensive Empirical Comparison of Domain Adaptation Methods for Neural Machine Translation
• タイトル / 言語: en
• タイトル: A Comprehensive Empirical Comparison of Domain Adaptation Methods for Neural Machine Translation
• 言語: eng
• キーワード / 主題Scheme: Other
• キーワード / 主題: [一般論文] neural machine translation, domain adaptation, empirical comparison
• 資源タイプ / 資源タイプ識別子: http://purl.org/coar/resource_type/c_6501
• 資源タイプ: journal article
• 著者所属: Institute for Datability Science, Osaka University
• 著者所属: Graduate School of Informatics, Kyoto University
• 著者所属: Graduate School of Informatics, Kyoto University
• 著者所属(英): en
• 著者所属(英): Institute for Datability Science, Osaka University
• 著者所属(英): en
• 著者所属(英): Graduate School of Informatics, Kyoto University
• 著者所属(英): en
• 著者所属(英): Graduate School of Informatics, Kyoto University
• 著者名: Chenhui, Chu; Raj, Dabre; Sadao, Kurohashi
• 著者名(英): Chenhui, Chu; Raj, Dabre; Sadao, Kurohashi
• 論文抄録 / 内容記述タイプ: Other
• 論文抄録 / 内容記述: Neural machine translation (NMT) has shown very promising results when there are large amounts of parallel corpora. However, for low resource domains, vanilla NMT cannot give satisfactory performance due to overfitting on the small size of parallel corpora. Two categories of domain adaptation approaches have been proposed for low resource NMT, i.e., adaptation using out-of-domain parallel corpora and in-domain monolingual corpora. In this paper, we conduct a comprehensive empirical comparison of the methods in both categories. For domain adaptation using out-of-domain parallel corpora, we further propose a novel domain adaptation method named mixed fine tuning, which combines two existing methods namely fine tuning and multi domain NMT. For domain adaptation using in-domain monolingual corpora, we compare two existing methods namely language model fusion and synthetic data generation. In addition, we propose a method that combines these two categories. We empirically compare all the methods and discuss their benefits and shortcomings. To the best of our knowledge, this is the first work on a comprehensive empirical comparison of domain adaptation methods for NMT.; ------------------------------; This is a preprint of an article intended for publication Journal of; Information Processing(JIP). This preprint should not be cited. This; article should be cited as: Journal of Information Processing Vol.26(2018) (online); DOI http://dx.doi.org/10.2197/ipsjjip.26.529; ------------------------------
• 論文抄録(英) / 内容記述タイプ: Other
• 論文抄録(英) / 内容記述: Neural machine translation (NMT) has shown very promising results when there are large amounts of parallel corpora. However, for low resource domains, vanilla NMT cannot give satisfactory performance due to overfitting on the small size of parallel corpora. Two categories of domain adaptation approaches have been proposed for low resource NMT, i.e., adaptation using out-of-domain parallel corpora and in-domain monolingual corpora. In this paper, we conduct a comprehensive empirical comparison of the methods in both categories. For domain adaptation using out-of-domain parallel corpora, we further propose a novel domain adaptation method named mixed fine tuning, which combines two existing methods namely fine tuning and multi domain NMT. For domain adaptation using in-domain monolingual corpora, we compare two existing methods namely language model fusion and synthetic data generation. In addition, we propose a method that combines these two categories. We empirically compare all the methods and discuss their benefits and shortcomings. To the best of our knowledge, this is the first work on a comprehensive empirical comparison of domain adaptation methods for NMT.; ------------------------------; This is a preprint of an article intended for publication Journal of; Information Processing(JIP). This preprint should not be cited. This; article should be cited as: Journal of Information Processing Vol.26(2018) (online); DOI http://dx.doi.org/10.2197/ipsjjip.26.529; ------------------------------
• 書誌レコードID / 収録物識別子タイプ: NCID
• 書誌レコードID / 収録物識別子: AN00116647
• 書誌情報: 情報処理学会論文誌; 巻 59, 号 7, 発行日 2018-07-15
• ISSN / 収録物識別子タイプ: ISSN
• ISSN / 収録物識別子: 1882-7764