Controlling Politeness in Neural Machine Translation via Side Constraints
Open accessThe DOI matches its Crossref record; 16 of the 18 references it cites were found in a registry or an index.
Abstract
Many languages use honorifics to express politeness, social distance, or the relative social status between the speaker and their addressee(s). In machine translation from a language without honorifics such as English, it is difficult to predict the appropriate honorific, but users may want to control the level of politeness in the output. In this paper, we perform a pilot study to control honorifics in neural machine translation (NMT) via side constraints, focusing on English!German. We show that by marking up the (English) source side of the training data with a feature that encodes the use of honorifics on the (German) target side, we can control the honorifics produced at test time. Experiments show that the choice of honorifics has a big impact on translation quality as measured by BLEU, and oracle experiments show that substantial improvements are possible by constraining the translation to the desired level of politeness.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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
THE PRONOUNS OF POWER AND SOLIDARITY
Brown, R., & Gilman, A. (1968) · Readings in the Sociology of Language · doi:10.1515/9783110805376.252 · Cited by 1,782 · cited 1×
“A wide-spread instance is the grammatical T-V distinction (Brown and Gilman, 1960), distinguishing between the familiar (Latin T u ) and the polite (Latin V os ) second person pronoun.”
BackgroundParallel Data, Tools and Interfaces in OPUS
Tiedemann, J. (2012) · Language Resources and Evaluation · Cited by 1,421
On Using Very Large Target Vocabulary for Neural Machine Translation
Jean, S., Cho, K., Memisevic, R., & Bengio, Y. (2015) · Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.3115/v1/p15-1001 · Cited by 862 · cited 4×
“We train an attentional encoder-decoder NMT system using Groundhog 2 (Bahdanau et al., 2015; Jean et al., 2015a).”
BackgroundMethodInfluentialContext dependent recurrent neural network language model
Mikolov, T., & Zweig, G. (2012) · 2012 IEEE Spoken Language Technology Workshop (SLT) · doi:10.1109/slt.2012.6424228 · Cited by 560 · cited 1×
“directly connecting them to all decoder hidden states, bypassing the attention model, or connecting them to the output layer (Mikolov and Zweig, 2012).”
BackgroundStanford neural machine translation systems for spoken language domains.
Luong, M.-T., & Manning, C. D. (2015) · Cited by 402
Montreal Neural Machine Translation Systems for WMT’15
Jean, S., Firat, O., Cho, K., Memisevic, R., & Bengio, Y. (2015) · Proceedings of the Tenth Workshop on Statistical Machine Translation · doi:10.18653/v1/w15-3014 · Cited by 134 · cited 3×
“We train an attentional encoder-decoder NMT system using Groundhog 2 (Bahdanau et al., 2015; Jean et al., 2015a).”
BackgroundMethodDocument Context Language Models
Ji, Y., Cohn, T., Kong, L., Dyer, C., & Eisenstein, J. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.03962 · Cited by 55 · cited 1×
“Previous research on neural language models has proposed including various types of extra information, such as topic, genre or document context (Mikolov and Zweig, 2012; Aransa et al., 2015; Ji et al., 2015; Wang and Cho, 2015).”
BackgroundLarger-Context Language Modelling with Recurrent Neural Network
Wang, T., & Cho, K. (2016) · Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p16-1125 · Cited by 47
Larger-Context Language ModellingPreprint
Wang, T., & Cho, K. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1511.03729 · Cited by 45
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
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
“In Sennrich et al.,(2016a), the NMT framework has been extended to control the politeness level of the target translation by adding a special token to the source sentence.”
BackgroundAdversarial Example Generation with Syntactically Controlled Paraphrase Networks
Iyyer, M., Wieting, J., Gimpel, K., & Zettlemoyer, L. (2018) · Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers) · doi:10.18653/v1/n18-1170 · Cited by 615
“language with user-selected properties such as sentence length and formality but is incapable of generating paraphrases. Formachinetranslationoutput,Niuetal.(2017) control the level of formality whileSennrich et al. (2016) control the level of politeness. For dialogue,Li et al.(2016a) affect the output using speaker i…”
BackgroundMethodLiu, P., Yuan, W., Fu, J., Jiang, Z., Hayashi, H., & Neubig, G. (2021) · arXiv · doi:10.48550/arxiv.2107.13586 · Cited by 4,352
Style transfer through back-translation
Prabhumoye, S., Tsvetkov, Y., Salakhutdinov, R., & Black, A. W. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1080 · Cited by 348
“…stylistic and demographic speaker traits in statistical machine translation (Rabinovich et al., 2016; Niu et al., 2017), and deep generative models controlling for a particular stylistic aspect, e.g., politeness (Sennrich et al., 2016), sentiment, or tense (Hu et al., 2017; Shen et al., 2017).”
Background
Metadata
- Authors
- Sennrich, R., Haddow, B., & Birch, A.
- Venue
- Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
- Published
- 2016
- Pages
- 35-40
- OpenAlex
- W2467834614
- Cited by
- 273
- References
- 18
- Citations by year
- 2026: 3 · 2025: 5 · 2024: 5 · 2023: 23 · 2022: 35 · 2021: 49 · 2020: 45 · 2019: 53 · 2018: 33 · 2017: 16 · 2016: 6
- FWCI
- 19.03
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) (publishedVersion, cc-by)
- Edinburgh Research Explorer (University of Edinburgh) (submittedVersion, cc-by)
- Funders
- European Commission (HORIZON2020, 644402)
- Samsung
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Social Sciences › Arts and Humanities › Language and Linguistics › Translation Studies and Practices
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Keywords
- honorifics, neural machine translation, side constraints, English-German translation, social distance, translation quality
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Controlling Politeness in Neural Machine Translation via Side Constraints. https://app.cochat.ai/papers/10.18653/v1/n16-1005
- The paper
- Sennrich, R., Haddow, B., & Birch, A. (2016). Controlling Politeness in Neural Machine Translation via Side Constraints. Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. https://doi.org/10.18653/v1/n16-1005
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.