An Empirical Comparison of Domain Adaptation Methods for Neural Machine Translation

被引：77

作者：

Chu, Chenhui ^{[1
,3
]}

Dabre, Raj ^{[2
]}

Kurohashi, Sadao ^{[2
]}

机构：

[1] Osaka Univ, Inst Databil Sci, Suita, Osaka, Japan

[2] Kyoto Univ, Grad Sch Informat, Kyoto, Japan

[3] Japan Sci & Technol Agcy, Kawaguchi, Saitama, Japan

来源：

PROCEEDINGS OF THE 55TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2017), VOL 2 | 2017年

关键词：

D O I：

10.18653/v1/P17-2061

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

In this paper, we propose a novel domain adaptation method named "mixed fine tuning" for neural machine translation (NMT). We combine two existing approaches namely fine tuning and multi domain NMT. We first train an NMT model on an out-of-domain parallel corpus, and then fine tune it on a parallel corpus which is a mix of the in-domain and out-of-domain corpora. All corpora are augmented with artificial tags to indicate specific domains. We empirically compare our proposed method against fine tuning and multi domain methods and discuss its benefits and shortcomings.

引用

页码：385 / 391

页数：7

共 50 条

[21] Domain Adaptation for Statistical Machine Translation
Wang, Xiaoxue
Zhu, Conghui
Li, Sheng
Zhao, Tiejun
Zheng, Dequan
2016 12TH INTERNATIONAL CONFERENCE ON NATURAL COMPUTATION, FUZZY SYSTEMS AND KNOWLEDGE DISCOVERY (ICNC-FSKD), 2016, : 1652 - 1658
[22] Efficient Machine Translation Domain Adaptation
Martins, Pedro Henrique
Marinhe, Zita
Martins, Andre F. T.
PROCEEDINGS OF THE 1ST WORKSHOP ON SEMIPARAMETRIC METHODS IN NLP: DECOUPLING LOGIC FROM KNOWLEDGE (SPA-NLP 2022), 2022, : 23 - 29
[23] An Empirical Study towards Characterizing Neural Machine Translation Testing Methods
He, Chenxi
Liu, Wenhong
Zhao, Shuang
Liu, Jiawei
Yang, Yang
2022 IEEE 22ND INTERNATIONAL CONFERENCE ON SOFTWARE QUALITY, RELIABILITY, AND SECURITY COMPANION, QRS-C, 2022, : 179 - 182
[24] Regularized Training Objective for Continued Training for Domain Adaptation in Neural Machine Translation
Khayrallah, Huda
Thompson, Brian
Duh, Kevin
Koehn, Philipp
NEURAL MACHINE TRANSLATION AND GENERATION, 2018, : 36 - 44
[25] Incremental Domain Adaptation for Neural Machine Translation in Low-Resource Settings
Kalimuthu, Marimuthu
Barz, Michael
Sonntag, Daniel
FOURTH ARABIC NATURAL LANGUAGE PROCESSING WORKSHOP (WANLP 2019), 2019, : 1 - 10
[26] Domain Adaptation in Neural Machine Translation using a Qualia-Enriched FrameNet
Costa, Alexandre Diniz
Marim, Mateus Coutinho
da Silva Matos, Ely Edison
Torrent, Tiago Timponi
LREC 2022: THIRTEEN INTERNATIONAL CONFERENCE ON LANGUAGE RESOURCES AND EVALUATION, 2022, : 1 - 12
[27] Simple, Scalable Adaptation for Neural Machine Translation
Bapna, Ankur
Firat, Orhan
2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019): PROCEEDINGS OF THE CONFERENCE, 2019, : 1538 - 1548
[28] Extreme Adaptation for Personalized Neural Machine Translation
Michel, Paul
Neubig, Graham
PROCEEDINGS OF THE 56TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 2, 2018, : 312 - 318
[29] A General Framework for Adaptation of Neural Machine Translation to Simultaneous Translation
Chen, Yun
Li, Liangyou
Jiang, Xin
Chen, Xiao
Liu, Qun
1ST CONFERENCE OF THE ASIA-PACIFIC CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS AND THE 10TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (AACL-IJCNLP 2020), 2020, : 191 - 200
[30] Effective domain awareness and adaptation approach via mask substructure for multi-domain neural machine translation
Huang, Shuanghong
Guo, Junjun
Yu, Zhengtao
Wen, Yonghua
NEURAL COMPUTING & APPLICATIONS, 2023, 35 (19): : 14047 - 14060

← 1 2 3 4 5 →