Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
38 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Gender Neutralization for an Inclusive Machine Translation: from Theoretical Foundations to Open Challenges (2301.10075v3)

Published 24 Jan 2023 in cs.CL

Abstract: Gender inclusivity in language technologies has become a prominent research topic. In this study, we explore gender-neutral translation (GNT) as a form of gender inclusivity and a goal to be achieved by machine translation (MT) models, which have been found to perpetuate gender bias and discrimination. Specifically, we focus on translation from English into Italian, a language pair representative of salient gender-related linguistic transfer problems. To define GNT, we review a selection of relevant institutional guidelines for gender-inclusive language, discuss its scenarios of use, and examine the technical challenges of performing GNT in MT, concluding with a discussion of potential solutions to encourage advancements toward greater inclusivity in MT.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize File Document Download Save Streamline Icon: https://streamlinehq.com PDF File Document Download Save Streamline Icon: https://streamlinehq.com Markdown Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (51)
  1. 2021. E-mimic: Empowering multilingual inclusive communication. In IEEE Big Data 2021, pages 4227–4234.
  2. 2005. METEOR: An automatic metric for MT evaluation with improved correlation with human judgments. In ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization, pages 65–72.
  3. 2020. Towards mitigating gender bias in a decoder-based neural machine translation model by adding contextual information. In The Fourth Widening Natural Language Processing Workshop, pages 99–102.
  4. 2018. Evaluating discourse phenomena in neural machine translation. In 16th NAACL HLT, pages 1304–1313.
  5. 2020. Gender in Danger? Evaluating Speech Translation Technology on the MuST-SHE Corpus. In 58th ACL, pages 6923–6933.
  6. 2020. Language (Technology) is Power: A Critical Survey of ``Bias'' in NLP. In 58th ACL, pages 5454–5476.
  7. 2003. Sex, syntax, and semantics. In Getner, Dedre and Susan Goldin-Meadow, editors, Language in Mind: Advances in the Study of Language and Thought, pages 61–79. MIT Press.
  8. 2022. “Es Geht Um Respekt, Nicht Um Technologie”: Erkenntnisse Aus Einem Interessensgruppen-üBergreifenden Workshop Zu Genderfairer Sprache Und Sprachtechnologie. In Mensch Und Computer 2022, page 106–118.
  9. Cameron, Deborah. 1995. Verbal Hygiene (The Politics of Language. Routledge.
  10. 2020. Toward gender-inclusive coreference resolution. In 58th ACL, pages 4568–4595.
  11. 2020. Lexical-constraint-aware neural machine translation via data augmentation. In 29th IJCAI, pages 3587–3593.
  12. 2019. On Measuring Gender Bias in Translation of Gender-neutral Pronouns. In First Workshop on Gender Bias in Natural Language Processing, pages 173–181.
  13. 2021. Input augmentation improves constrained beam search for neural machine translation: NTT at WAT 2021. In 8th Workshop on Asian Translation, pages 53–61.
  14. Comandini, Gloria. 2021. Salve a tutt, tutt*, tuttu, tuttx e tutt@: l’uso delle strategie di neutralizzazione di genere nella comunità queer online. : Indagine su un corpus di italiano scritto informale sul web. Testo e Senso, 23:43–64.
  15. Crenshaw, Kimberle Williams. 1991. Mapping the margins: Intersectionality, identity politics, and violence against women of color. Stanford Law Review, 43(6):1241–99.
  16. 2021. Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies. In EMNLP 2021, pages 1968–1994.
  17. 2019. Training neural machine translation to apply terminology constraints. In 57th ACL, pages 3063–3068.
  18. 2002. Near-synonymy and lexical choice. Computational Linguistics, 28(2):105–144.
  19. 2022. Why is constrained neural language generation particularly challenging? ArXiv e-prints arXiv:2206.05395.
  20. 2008. Generically Intended, but Specifically Interpreted: When Beauticians, Musicians and Mechanics are all Men. Language and Cognitive Processes, 23:464–485.
  21. 2019. A Language Index of Grammatical Gender Dimensions to Study the Impact of Grammatical Gender on the Way We Perceive Women and Men. Frontiers in Psychology, 10.
  22. He, Guimei. 2010. An analysis of sexism in english. Journal of Language Teaching and Research, 1(3):332–335.
  23. 2007. Handbook of Language and Communication: Diversity and Change. De Gruyter Mouton.
  24. 2017. Lexically constrained decoding for sequence generation using grid beam search. In 55th ACL, pages 1535–1546.
  25. Kiesling, Scott F. 2019. Language, Gender, and Sexuality: An introduction. Routledge.
  26. 2019. When and Why is Document-level Context Useful in Neural Machine Translation? In Fourth Workshop on Discourse in Machine Translation, pages 24–34.
  27. 2022. Welcome to the Modern World of Pronouns: Identity-Inclusive Natural Language Processing beyond Gender. In 29th COLING, pages 1221–1232.
  28. Lazar, Michelle M. 2005. Politicizing gender in discourse: Feminist critical discourse analysis as political perspective and praxis. In Lazar, Michelle M., editor, Feminist Critical Discourse Analysis: Gender, Power and Ideology in Discourse, pages 1–28.
  29. 2020. Does multi-encoder help? a case study on context-aware neural machine translation. In 58th ACL, pages 3512–3518.
  30. 2020. Document-level neural MT: A systematic comparison. In 22nd EAMT, pages 225–234.
  31. 2002. BLEU: a Method for Automatic Evaluation of Machine Translation. In 40th ACL, pages 311–318.
  32. Popović, Maja. 2015. chrF: character n-gram F-score for automatic MT evaluation. In WMT15, pages 392–395.
  33. 2018. Fast lexically constrained decoding with dynamic beam allocation for neural machine translation. In 16th NAACL HLT, pages 1314–1324.
  34. 2020. Assessing gender bias in machine translation: a case study with google translate. Neural Computing and Applications, 32(10):6363–6381.
  35. 2015. Truly exploring multiple references for machine translation evaluation. In 18th EAMT.
  36. 2020. COMET: A Neural Framework for MT Evaluation. In EMNLP 2020, pages 2685–2702.
  37. 2019. Integration of dubbing constraints into machine translation. In WMT19, pages 94–101.
  38. 2020. Reducing gender bias in neural machine translation as a domain adaptation problem. In 58th ACL, pages 7724–7736.
  39. 2022. First the worst: Finding better gender translations during beam search. Findings of 60th ACL, pages 3814–3823.
  40. 2021. Gender bias in machine translation. TACL, 9:845–874.
  41. 2022. Under the morphosyntactic lens: A multifaceted evaluation of gender bias in speech translation. In 60th ACL, pages 1807–1824.
  42. 2006. A Study of Translation Edit Rate with Targeted Human Annotation. In 7th AMTA, pages 223–231.
  43. 2019. Code-switching for enhancing NMT with pre-specified translation. In 17th NAACL HLT, pages 449–459.
  44. 2020. Mitigating Gender Bias in Machine Translation with Target Gender Annotations. In WMT20, pages 629–638.
  45. 2007. Representation of the Sexes in Language. Social communication, pages 163–187.
  46. 2019. Evaluating Gender Bias in Machine Translation. In 57th ACL, pages 1679–1684.
  47. 2021. They, Them, Theirs: Rewriting with Gender-Neutral English. arXiv preprint arXiv:2102.06788.
  48. van Deemter, Kees. 2009. Utility and language generation: The case of vagueness. Journal of Philosophical Logic, 38(6):607–632.
  49. 2018. Getting gender right in neural machine translation. In EMNLP 2018, pages 3003–3008.
  50. 2021. NeuTral Rewriter: A rule-based and neural approach to automatic rewriting into gender neutral alternatives. In EMNLP 2021, pages 8940–8948.
  51. 2009. ¿qué? quoi? do languages with grammatical gender promote sexist attitudes? Sex Roles: A Journal of Research, 61:634–643.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Andrea Piergentili (6 papers)
  2. Dennis Fucci (11 papers)
  3. Beatrice Savoldi (19 papers)
  4. Luisa Bentivogli (38 papers)
  5. Matteo Negri (93 papers)
Citations (11)
View on Semantic Scholar