Getting Gender Right in Neural Machine Translation

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 two-fold: (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.

arXiv commentProceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), October-November, 2018. Brussels, Belgium, pages 3003-3008, URL: https://www.aclweb.org/anthology/D18-1334, DOI: 10.18653/v1/D18-1334

References in corpus (2)

• Neural Machine Translation by Jointly Learning to Align and Translate
• Sequence to Sequence Learning with Neural Networks

Cited by in corpus (32)

• Gender bias and stereotypes in Large Language Models
• Representation Bias in Data: A Survey on Identification and Resolution Techniques
• Dataset for Identification of Homophobia and Transophobia in Multilingual YouTube Comments
• Lost in Translation: Loss and Decay of Linguistic Richness in Machine Translation
• Equalizing Gender Biases in Neural Machine Translation with Word Embeddings Techniques
• Mitigating Gender Bias in Natural Language Processing: Literature Review
• Gender Bias in Contextualized Word Embeddings
• Neural Machine Translation Doesn't Translate Gender Coreference Right Unless You Make It
• Mitigating Gender Bias in Machine Translation with Target Gender Annotations
• Decoding and Diversity in Machine Translation
• Towards an Enhanced Understanding of Bias in Pre-trained Neural Language Models: A Survey with Special Emphasis on Affective Bias
• Societal Biases in Language Generation: Progress and Challenges
• Improving Gender Translation Accuracy with Filtered Self-Training
• MT-Adapted Datasheets for Datasets: Template and Repository
• Disembodied Machine Learning: On the Illusion of Objectivity in NLP
• On the Integration of LinguisticFeatures into Statistical and Neural Machine Translation
• Dictionary-based Debiasing of Pre-trained Word Embeddings
• Document-aligned Japanese-English Conversation Parallel Corpus
• RAMP: Retrieval and Attribute-Marking Enhanced Prompting for Attribute-Controlled Translation
• Argument from Old Man's View: Assessing Social Bias in Argumentation
• Token-level Adaptive Training for Neural Machine Translation
• ABI Neural Ensemble Model for Gender Prediction Adapt Bar-Ilan Submission for the CLIN29 Shared Task on Gender Prediction
• Controlling Text Complexity in Neural Machine Translation
• Towards Socially Responsible AI: Cognitive Bias-Aware Multi-Objective Learning
• Faithful Target Attribute Prediction in Neural Machine Translation
• Mitigating Gender Bias in Captioning Systems
• Distilling Translations with Visual Awareness
• GENder-IT: An Annotated English-Italian Parallel Challenge Set for Cross-Linguistic Natural Gender Phenomena
• Scalable Cross Lingual Pivots to Model Pronoun Gender for Translation
• NeuTral Rewriter: A Rule-Based and Neural Approach to Automatic Rewriting into Gender-Neutral Alternatives
• Repairing Pronouns in Translation with BERT-Based Post-Editing
• Machine Translation for Machines: the Sentiment Classification Use Case