An Empirical Comparison of Domain Adaptation Methods for Neural Machine Translation
Open accessThe DOI matches its Crossref record; 25 of the 28 references it cites were found in a registry or an index.
Abstract
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-ofdomain 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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Specifically, the guidance signals could be style tokens [27,123], length specifications [56], domain tags [14], or any variety of other pieces of information used to control of the generated text.”
From Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing (2023) · cites this paper as [14]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1179 · Cited by 25,545 · cited 2×
“One of the most attractive features of neural machine translation (NMT) (Bahdanau et al., 2015; Cho et al., 2014; Sutskever et al., 2014) is that it is possible to train an end to end system without the need to deal with word alignments, translation rules and complicated decoding algorithms, which are a characteristic…”
BackgroundSequence to Sequence Learning with Neural Networks
Sutskever, I., Vinyals, O., & Le, Q. V. (2014) · arXiv · doi:10.48550/arxiv.1409.3215 · Cited by 17,766 · cited 1×
“One of the most attractive features of neural machine translation (NMT) (Bahdanau et al., 2015; Cho et al., 2014; Sutskever et al., 2014) is that it is possible to train an end to end system without the need to deal with word alignments, translation rules and complicated decoding algorithms, which…”
BackgroundNeural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213 · cited 2×
“One of the most attractive features of neural machine translation (NMT) (Bahdanau et al., 2015; Cho et al., 2014; Sutskever et al., 2014) is that it is possible to train an end to end system without the need to deal with word alignments, translation rules and complicated decoding algorithms, which are a characteristic…”
BackgroundMoses: open source toolkit for statistical machine translation
Koehn, P., Zens, R., Dyer, C., Bojar, O., Constantin, A., Herbst, E., Hoang, H., Birch, A., Callison-Burch, C., Federico, M., et al. (2007) · Proceedings of the 45th Annual Meeting of the ACL on Interactive Poster and Demonstration Sessions - ACL '07 · doi:10.3115/1557769.1557821 · Cited by 4,735 · cited 1×
“We used the Moses PBSMT system (Koehn et al., 2007) for all of our MT experiments.”
MethodMinimum error rate training in statistical machine translation
Och, F. J. (2003) · Proceedings of the 41st Annual Meeting on Association for Computational Linguistics - ACL '03 · doi:10.3115/1075096.1075117 · Cited by 2,725 · cited 1×
“In all of our experiments, we used the GIZA++ toolkit 7 for word alignment; tuning was performed by minimum error rate training (Och, 2003), and it was re-run for every experiment.”
MethodStatistical Significance Tests for Machine Translation Evaluation.
Koehn, P. (2004) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · Cited by 2,165
Google’s Multilingual Neural Machine Translation System: Enabling Zero-Shot Translation
Johnson, M., Schuster, M., Le, Q. V., Krikun, M., Wu, Y., Chen, Z., Thorat, N., Viégas, F., Wattenberg, M., Corrado, G., et al. (2017) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00065 · Cited by 1,747 · cited 1×
“Tag based NMT has also been shown to be effective for control the politeness of translations (Sennrich et al., 2016a) and multilingual NMT (Johnson et al., 2016).”
BackgroundMoses : open source toolkit for statistical machine translation
Koehn, P., Hoang, H., Birch, A., Callison-Burch, C., Federico, M., Bertoldi, N., Cowan, B., Shen, W., Moran, C., Zens, R., et al. (2007) · Edinburgh Research Explorer (University of Edinburgh) · Cited by 1,547
Transfer Learning for Low-Resource Neural Machine Translation
Zoph, B., Yuret, D., May, J., & Knight, K. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1163 · Cited by 788 · cited 8×
“However, it is reported that NMT works better than SMT only when there is an abundance of parallel corpora.”
BackgroundInfluentialStanford neural machine translation systems for spoken language domains.
Luong, M.-T., & Manning, C. D. (2015) · Cited by 499
On Using Monolingual Corpora in Neural Machine Translation
Gülçehre, Ç., Fırat, O., Xu, K., Cho, K., Barrault, L., Lin, H.-C., Bougares, F., Schwenk, H., & Bengio, Y. (2015) · HAL (Le Centre pour la Communication Scientifique Directe) · doi:10.48550/arxiv.1503.03535 · Cited by 466 · cited 2×
“Either training an in-domain recurrent neural network (RNN) language model for the NMT decoder (Gülçehre et al., 2015) or generating synthetic data by back translating target in-domain monolingual data (Sennrich et al., 2016b) have been studied.”
BackgroundMethodControlling Politeness in Neural Machine Translation via Side Constraints
Sennrich, R., Haddow, B., & Birch, A. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/n16-1005 · Cited by 273 · cited 9×
“Tag based NMT has also been shown to be effective for control the politeness of translations (Sennrich et al., 2016a) and multilingual NMT (Johnson et al., 2016).”
BackgroundMethodInfluentialHow Transferable are Neural Networks in NLP Applications?
Mou, L., Meng, Z., Yan, R., Li, G., Xu, Y., Zhang, L., & Jin, Z. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1046 · Cited by 259 · cited 1×
“Fine tuning has also been explored for various NLP tasks using neural networks such as sentiment analysis and paraphrase detection (Mou et al., 2016).”
MethodOverview of the patent machine translation task at the NTCIR-9 workshop
Goto, I., Lu, B., Chow, K. P., Sumita, E., & Tsou, B. K. (2011) · NTCIR · Cited by 178
ASPEC: Asian Scientific Paper Excerpt Corpus
Nakazawa, T., Yaguchi, M., Uchimoto, K., Utiyama, M., Sumita, E., Kurohashi, S., & Isahara, H. (2016) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/3iku22jbpbzm · Cited by 166 · cited 3×
“The scientific domain MT was conducted on the Chinese-Japanese paper excerpt corpus (ASPEC-CJ)3 (Nakazawa et al., 2016), which is one subtask of the workshop on Asian translation (WAT)4 (Nakazawa et al.”
BackgroundMethodInfluentialSelf-citationFast Domain Adaptation for Neural Machine Translation
Freitag, M., & Al-Onaizan, Y. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.06897 · Cited by 151 · cited 2×
“The conventional domain adaptation method is fine tuning , in which an out-of-domain model is further trained on in-domain data (Luong and Manning, 2015; Sen-nrich et al., 2016b; Servan et al., 2016; Freitag and Al-Onaizan, 2016).”
MethodDomain Control for Neural Machine Translation
SYSTRAN International, P., Kobus, C., Crego, J., & Senellart, J. (2017) · RANLP 2017 - Recent Advances in Natural Language Processing Meet Deep Learning · doi:10.26615/978-954-452-049-6_049 · Cited by 135 · cited 1×
“On the other hand, multi domain NMT (Kobus et al., 2016) involves training a single NMT model for multiple domains.”
BackgroundOverview of the 8th Workshop on Asian Translation
Nakazawa, T., Nakayama, H., Ding, C., Dabre, R., Higashiyama, S., Mino, H., Goto, I., Pa, W. P., Kunchukuttan, A., Parida, S., et al. (2021) · Workshop on Asian Translation (WAT) · doi:10.18653/v1/2021.wat-1.1 · Cited by 111
Self-citationGoogle's Multilingual Neural Machine Translation System: Enabling Zero-Shot TranslationPreprint
Johnson, M., Schuster, M., Le, Q. V., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1611.04558 · Cited by 109 · cited 1×
“Tag based NMT has also been shown to be effective for control the politeness of translations (Sennrich et al., 2016a) and multilingual NMT (Johnson et al., 2016).”
BackgroundThe IWSLT 2015 Evaluation Campaign
Cettolo, M., Niehues, J., Stüker, S., Bentivogli, L., Cattoni, R., & Federico, M. (2015) · Repository KITopen (Karlsruhe Institute of Technology) · doi:10.5281/zenodo.1326521 · Cited by 95
Overview of the 7th Workshop on Asian Translation
Nakazawa, T., Nakayama, H., Ding, C., Dabre, R., Higashiyama, S., Mino, H., Goto, I., Pa, W. P., Kunchukuttan, A., Parida, S., et al. (2020) · Workshop on Asian Translation (WAT) · doi:10.18653/v1/2020.wat-1.1 · Cited by 66
Self-citationDomain specialization: a post-training domain adaptation for Neural Machine TranslationPreprint
Servan, C., Crego, J., & Sénellart, J. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.06141 · Cited by 43 · cited 1×
“The conventional domain adaptation method is fine tuning , in which an out-of-domain model is further trained on in-domain data (Luong and Manning, 2015; Sen-nrich et al., 2016b; Servan et al., 2016; Freitag and Al-Onaizan, 2016).”
MethodDomain Control for Neural Machine TranslationPreprint
Kobus, C., Crego, J., & Sénellart, J. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1612.06140 · Cited by 35 · cited 1×
“On the other hand, multi domain NMT (Kobus et al., 2016) involves training a single NMT model for multiple domains.”
BackgroundParallel Sentence Extraction from Comparable Corpora with Neural Network Features
Chu, C., Dabre, R., & Kurohashi, S. (2016) · Language Resources and Evaluation Conference (LREC) · doi:10.63317/33ujzhai4ek7 · Cited by 7 · cited 9×
“We can see that without domain adaptation, the SMT systems perform significantly better than the NMT system on the resource poor domains, i.e., IWSLT-CE and WIKI-CJ; while on the resource rich domains, i.e., NTCIR-CE and ASPECCJ, NMT outperforms SMT. Directly using the SMT/NMT models trained on the out-of-domain data…”
MethodInfluentialSelf-citationSCTB: A Chinese Treebank in Scientific Domain
Chu, C., Nakazawa, T., Kawahara, D., & Kurohashi, S. (2016) · International Conference on Computational Linguistics · Cited by 4
Self-citation
Research works printed but not linked: 4
- [6]6. Fabien Cromieres, Chenhui Chu, Toshiaki Nakazawa, and Sadao Kurohashi. 2016. Kyoto univer- sity participation to wat 2016. In Proceed- ings of the 3rd Workshop on Asian Transla- tion (WAT2016). The COLING 2016 Organiz- ing Committee, Osaka, Japan, pages 166-174. http://aclweb.org/anthology/W16-4616.
- [14]14. Sadao Kurohashi, Toshihisa Nakamura, Yuji Mat- sumoto, and Makoto Nagao. 1994. Improvements of Japanese morphological analyzer JUMAN. In Pro- ceedings of the International Workshop on Sharable Natural Language. pages 22-28.
- [21]21. Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016b. Improving neural machine translation models with monolingual data. In Proceed- ings of the 54th Annual Meeting of the As- sociation for Computational Linguistics (Volume 1: Long Papers). Association for Computa- tional Linguistics, Berlin, Germany, pages 86-96. http://www.aclweb.org/anthology/P16-1009.
- [22]22. Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016c. Neural machine translation of rare words with subword units. In Proceed- ings of the 54th Annual Meeting of the As- sociation for Computational Linguistics (Volume 1: Long Papers). Association for Computational Linguistics, Berlin, Germany, pages 1715-1725. http://www.aclweb.org/anthology/P16-1162.
Cited by
Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2023) · ACM Computing Surveys · doi:10.1145/3560815 · Cited by 4,361
Liu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2021) · arXiv · doi:10.48550/arxiv.2107.13586 · Cited by 4,352
Koehn, P. (2020) · Cambridge University Press eBooks · doi:10.1017/9781108608480 · Cited by 236
A Survey of Multilingual Neural Machine Translation
Dabre, R., Chu, C., & Kunchukuttan, A. (2021) · ACM Computing Surveys · doi:10.1145/3406095 · Cited by 294
“Therefore, similar to MNMT, when using out-ofdomain parallel corpora for domain adaptation, multi-domain NMT and transfer-learning-based approaches [29] have been proposed for domain adaptation.”
MethodSelf-citationA Survey of Domain Adaptation for Machine Translation
Chu, C., & Wang, R. (2020) · Journal of Information Processing · doi:10.2197/ipsjjip.28.413 · Cited by 282
“MT typically performs poorly in a resource poor or domain mismatching scenario and thus it is important to leverage the spoken language domain data with the patent domain data [20].”
BackgroundMethodInfluentialSelf-citation
Metadata
- Authors
- Chu, C., Dabre, R., & Kurohashi, S.
- Affiliations
- The University of Osaka (JP)
- Kyoto University (JP)
- Corresponding author
- Chu, Chenhui
- Venue
- Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)
- Published
- 2017
- Pages
- 385-391
- ISSN
- 0736-587X (ISSN-L)
- OpenAlex
- W2744813330
- Cited by
- 215
- References
- 28
- Citations by year
- 2025: 15 · 2024: 15 · 2023: 21 · 2022: 21 · 2021: 27 · 2020: 41 · 2019: 39 · 2018: 27 · 2017: 9
- FWCI
- 14.47
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Proceedings of the conference - Association for Computational Linguistics. Meeting (publishedVersion, cc-by)
- Funders
- Department of Science and Technology, Ministry of Science and Technology, India
- Japan Society for the Promotion of Science
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- domain adaptation, neural machine translation, fine-tuning
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.

