Getting Gender Right in Neural Machine Translation
Open accessThe DOI matches its Crossref record; 4 of the 4 references it cites were found in a registry or an index.
Abstract
Speakers of different languages must attend to and encode strikingly different aspects of the world in order to use their language correctly (Sapir, 1921;Slobin, 1996).One such difference is related to the way gender is expressed in a language.Saying "I am happy" in English, does not encode any additional knowledge of the speaker that uttered the sentence.However, many other languages do have grammatical gender systems and so such knowledge would be encoded.In order to correctly translate such a sentence into, say, French, the inherent gender information needs to be retained/recovered.The same sentence would become either "Je suis heureux", for a male speaker or "Je suis heureuse" for a female one.Apart from morphological agreement, demographic factors (gender, age, etc.) also influence our use of language in terms of word choices or even on the level of syntactic constructions (Tannen, 1991;Pennebaker et al., 2003).We integrate gender information into NMT systems.Our contribution is twofold: (1) the compilation of large datasets with speaker information for 20 language pairs, and (2) a simple set of experiments that incorporate gender information into NMT for multiple language pairs.Our experiments show that adding a gender feature to an NMT system significantly improves the translation quality for some language pairs.
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
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.
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
BLEU: a method for automatic evaluation of machine translation
Papineni, K., Roukos, S., Ward, T., & Zhu, W.-J. (2001) · Proceedings of the 40th Annual Meeting on Association for Computational Linguistics - ACL '02 · doi:10.3115/1073083.1073135 · Cited by 21,344
Psychological Aspects of Natural Language Use: Our Words, Our Selves
Pennebaker, J. W., Mehl, M. R., & Niederhoffer, K. G. (2003) · Annual Review of Psychology · doi:10.1146/annurev.psych.54.101601.145041 · Cited by 2,624 · cited 1×
“) also influence our use of language in terms of word choices or even on the level of syntactic constructions (Tannen, 1991; Pennebaker et al., 2003).”
BackgroundGender differences in language use: An analysis of 14,000 text samples
Newman, M. L., Groom, C. J., Handelman, L. D., & Pennebaker, J. W. (2008) · Discourse Processes · doi:10.1080/01638530802073712 · Cited by 788 · cited 2×
“…linguistic studies, which have shown that gender does not only have an effect on morphological agreement, but also manifests itself in other ways as males and females have different preferences when it comes to different types of constructions, word choices etc. (Newman et al., 2008; Coates, 2015).”
BackgroundResultControlling 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 2×
“Our approach is similar to the work of Sennrich et al. (2016) on controlling politeness, where some sentence of the training data are followed with an ‘informal’ or ‘polite’ tag indicating the level of politeness expressed.”
Method
Cited by
A Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2022) · ACM Computing Surveys · doi:10.1145/3457607 · Cited by 5,812
A Survey on Bias and Fairness in Machine Learning
Mehrabi, N., Morstatter, F., Saxena, N., Lerman, K., & Galstyan, A. (2019) · arXiv · doi:10.48550/arxiv.1908.09635 · Cited by 5,812
Language (Technology) is Power: A Critical Survey of “Bias” in NLP
Blodgett, S. L., Barocas, S., Daumé III, H., & Wallach, H. (2020) · Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/2020.acl-main.485 · Cited by 1,050
“…language modeling (Lu et al., 2018; Bordia and Bowman, 2019), coreference resolution (Rudinger et al., 2018; Zhao et al., 2018a), machine translation (Vanmassenhove et al., 2018; Stanovsky et al., 2019), sentiment analysis (Kiritchenko and Mohammad, 2018), and hate speech/toxicity detection…”
BackgroundMethodA Review on Fairness in Machine Learning
Pessach, D., & Shmueli, E. (2023) · ACM Computing Surveys · doi:10.1145/3494672 · Cited by 598
“Let us note that the challenges of fair word embedding also affect many other downstream applications that use these word representations, for example, in coreference resolution [173, 220, 222], in sentence encoding [146], in machine translation [75, 203], in language models [27], and in semantic role labeling [221].”
BackgroundMitigating Gender Bias in Natural Language Processing: Literature Review
Sun, T., Gaut, A., Tang, S., Huang, Y., ElSherief, M., Zhao, J., Mirza, D., Belding, E., Chang, K.-W., & Wang, W. Y. (2019) · Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · doi:10.18653/v1/p19-1159 · Cited by 492
“This happens because training sets are dominated by male-sourced data points, so the models learn skewed statistical relationships and are thus more likely to predict the speaker to be male when the gender of the source is ambiguous (Vanmassenhove et al., 2018).”
BackgroundMethodInfluentialGender bias and stereotypes in Large Language Models
Kotek, H., Dockum, R., & Sun, D. (2023) · Proceedings of The ACM Collective Intelligence Conference · doi:10.1145/3582269.3615599 · Cited by 381
Gender Bias in Contextualized Word Embeddings
Zhao, J., Wang, T., Yatskar, M., Cotterell, R., Ordonez, V., & Chang, K.-W. (2019) · Proceedings of the 2019 Conference of the North · doi:10.18653/v1/n19-1064 · Cited by 319
Popel, M., Tomkova, M., Tomek, J., Kaiser, Ł., Uszkoreit, J., Bojar, O., & Žabokrtský, Z. (2020) · Nature Communications · doi:10.1038/s41467-020-18073-9 · Cited by 299
Trustworthy ai: A computational perspective
Liu, H., Wang, Y., Fan, W., Liu, X., Li, Y., Jain, S., Liu, Y., Jain, A., & Tang, J. (2023) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3546872 · Cited by 261
Societal Biases in Language Generation: Progress and Challenges
Sheng, E., Chang, K.-W., Natarajan, P., & Peng, N. (2021) · Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.18653/v1/2021.acl-long.330 · Cited by 131
“The second category is methods that attach a short prefix at training time (Vanmassenhove et al., 2018; Basta et al., 2020; Alhafni et al., 2020) or inference time (Moryossef et al., 2019).”
MethodMitigating Gender Bias in Captioning Systems
Tang, R., Du, M., Li, Y., Liu, Z., Zou, N., & Hu, X. (2021) · Proceedings of the Web Conference 2021 · doi:10.1145/3442381.3449950 · Cited by 50
Cao, Y. T., & Daumé, H. (2021) · Computational Linguistics · doi:10.1162/coli_a_00413 · Cited by 47
Vanmassenhove, E., Emmery, C., & Shterionov, D. (2021) · Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/2021.emnlp-main.704 · Cited by 35
“Within the field of Machine Translation (MT), Vanmassenhove and Hardmeier (2018); Vanmas-senhove et al. (2019), and Basta et al. (2020) in-a corporate meta-information in the form of gender tags on the source side to enable gender alternative target translations for ambiguous source sentences.”
BackgroundSelf-citationDisembodied Machine Learning: On the Illusion of Objectivity in NLP
Waseem, Z., Lulz, S., Bingel, J., & Augenstein, I. (2021) · arXiv · doi:10.48550/arxiv.2101.11974 · Cited by 34
When Do Pre-Training Biases Propagate to Downstream Tasks? A Case Study in Text Summarization
Ladhak, F., Durmus, E., Suzgun, M., Zhang, T., Jurafsky, D., McKeown, K., & Hashimoto, T. (2023) · Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2023.eacl-main.234 · Cited by 30
Towards User-Centric Text-to-Text Generation: A Survey
Yang, D., & Flek, L. (2021) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-83527-9_1 · Cited by 10
Metadata
- Authors
- Vanmassenhove, E., Hardmeier, C., & Way, A.
- Venue
- Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
- Published
- 2018
- Pages
- 3003-3008
- OpenAlex
- W2972972637
- Cited by
- 153
- References
- 4
- FWCI
- 9.47
- Type
- conference paper
- Language
- en
- Open access
- hybrid
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.