Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 416.00 KB
Add to list
  1. Search results
  2. You shall know a word’s gender by the...

You shall know a word’s gender by the company it keeps : comparing the role of context in human gender assumptions with MT

Janica Hackenbuchner (UGent) , Arda Tezcan (UGent) , Aaron Maladry (UGent) and Joke Daems (UGent)
(2024) Proceedings of the 2nd International Workshop on Gender-Inclusive Translation Technologies. p.31-41
Author
Organization
Project
Abstract
In this paper, we analyse to what extent machine translation (MT) systems and humans base their gender translations and associations on role names and on stereotypicality in the absence of (generic) grammatical gender cues in language. We compare an MT system’s choice of gender for a certain word when translating from a notional gender language, English, into a grammatical gender language, German, with the gender associations of humans. We outline a comparative case study of gender translation and annotation of words in isolation, out-of-context, and words in sentence contexts. The analysis reveals patterns of gender (bias) by MT and gender associations by humans for certain (1) out-of-context words and (2) words in-context. Our findings reveal the impact of context on gender choice and translation and show that wordlevel analyses fall short in such studies.

Downloads

  • Download
    GITT 2024 pp31-41.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 416.00 KB

Citation

Please use this url to cite or link to this publication:

MLA
Hackenbuchner, Janica, et al. “You Shall Know a Word’s Gender by the Company It Keeps : Comparing the Role of Context in Human Gender Assumptions with MT.” Proceedings of the 2nd International Workshop on Gender-Inclusive Translation Technologies, edited by Beatrice Savoldi et al., Association for Computational Linguistics (ACL), 2024, pp. 31–41.
APA
Hackenbuchner, J., Tezcan, A., Maladry, A., & Daems, J. (2024). You shall know a word’s gender by the company it keeps : comparing the role of context in human gender assumptions with MT. In B. Savoldi, J. Hackenbuchner, L. Bentivogli, J. Daems, E. Vanmassenhove, & J. Bastings (Eds.), Proceedings of the 2nd International Workshop on Gender-Inclusive Translation Technologies (pp. 31–41). Association for Computational Linguistics (ACL).
Chicago author-date
Hackenbuchner, Janica, Arda Tezcan, Aaron Maladry, and Joke Daems. 2024. “You Shall Know a Word’s Gender by the Company It Keeps : Comparing the Role of Context in Human Gender Assumptions with MT.” In Proceedings of the 2nd International Workshop on Gender-Inclusive Translation Technologies, edited by Beatrice Savoldi, Janica Hackenbuchner, Luisa Bentivogli, Joke Daems, Eva Vanmassenhove, and Jasmijn Bastings, 31–41. Association for Computational Linguistics (ACL).
Chicago author-date (all authors)
Hackenbuchner, Janica, Arda Tezcan, Aaron Maladry, and Joke Daems. 2024. “You Shall Know a Word’s Gender by the Company It Keeps : Comparing the Role of Context in Human Gender Assumptions with MT.” In Proceedings of the 2nd International Workshop on Gender-Inclusive Translation Technologies, ed by. Beatrice Savoldi, Janica Hackenbuchner, Luisa Bentivogli, Joke Daems, Eva Vanmassenhove, and Jasmijn Bastings, 31–41. Association for Computational Linguistics (ACL).
Vancouver
1.
Hackenbuchner J, Tezcan A, Maladry A, Daems J. You shall know a word’s gender by the company it keeps : comparing the role of context in human gender assumptions with MT. In: Savoldi B, Hackenbuchner J, Bentivogli L, Daems J, Vanmassenhove E, Bastings J, editors. Proceedings of the 2nd International Workshop on Gender-Inclusive Translation Technologies. Association for Computational Linguistics (ACL); 2024. p. 31–41.
IEEE
[1]
J. Hackenbuchner, A. Tezcan, A. Maladry, and J. Daems, “You shall know a word’s gender by the company it keeps : comparing the role of context in human gender assumptions with MT,” in Proceedings of the 2nd International Workshop on Gender-Inclusive Translation Technologies, Sheffield, UK, 2024, pp. 31–41.
@inproceedings{01HXVJZFK4JTH8SD2TVQTM1J6H,
  abstract     = {{In this paper, we analyse to what extent machine translation (MT) systems and humans base their gender translations and associations on role names and on stereotypicality in the absence of (generic) grammatical gender cues in language. We compare an MT system’s choice of gender for a certain word when translating from a notional gender language, English, into a grammatical gender language, German, with the gender associations of humans. We outline a comparative case study of gender translation and annotation of words in isolation, out-of-context, and words in sentence contexts. The analysis reveals patterns of gender (bias) by MT and gender associations by humans for certain (1) out-of-context words and (2) words in-context. Our findings reveal the impact of context on gender choice and translation and show that wordlevel analyses fall short in such studies.}},
  author       = {{Hackenbuchner, Janica and Tezcan, Arda and Maladry, Aaron and Daems, Joke}},
  booktitle    = {{Proceedings of the 2nd International Workshop on Gender-Inclusive Translation Technologies}},
  editor       = {{Savoldi, Beatrice and Hackenbuchner, Janica and Bentivogli, Luisa and Daems, Joke and Vanmassenhove, Eva and Bastings, Jasmijn}},
  isbn         = {{9781068690723}},
  language     = {{eng}},
  location     = {{Sheffield, UK}},
  pages        = {{31--41}},
  publisher    = {{Association for Computational Linguistics (ACL)}},
  title        = {{You shall know a word’s gender by the company it keeps : comparing the role of context in human gender assumptions with MT}},
  url          = {{https://aclanthology.org/2024.gitt-1.0.pdf}},
  year         = {{2024}},
}