Lost in Translation? Approaches to Gender Representation in Multilingual Archives

Mrinalini Luthra, Brecht Nijman


Abstract
The GLOBALISE project’s digitalisation of the Dutch East India Company (VOC) archives raises questions about representing gender and marginalised identities. This paper outlines the challenges of accurately conveying gender information in the archives, highlighting issues such as the lack of self-identified gender descriptions, low representation of marginalised groups, colonial context, and multilingualism in the collection. Machine learning (ML) and machine translation (MT) used in the digitalisation process may amplify existing biases and under-representation. To address these issues, the paper proposes a gender policy for GLOBALISE, offering guidelines and methodologies for handling gender information and increasing the visibility of marginalised identities. The policy contributes to discussions about representing gender and diversity in digital historical research, ML, and MT.
Anthology ID:
2024.gitt-1.5
Volume:
Proceedings of the 2nd International Workshop on Gender-Inclusive Translation Technologies
Month:
June
Year:
2024
Address:
Sheffield, United Kingdom
Editors:
Beatrice Savoldi, Janiça Hackenbuchner, Luisa Bentivogli, Joke Daems, Eva Vanmassenhove, Jasmijn Bastings
Venues:
GITT | WS
SIG:
Publisher:
European Association for Machine Translation (EAMT)
Note:
Pages:
42–55
Language:
URL:
https://aclanthology.org/2024.gitt-1.5
DOI:
Bibkey:
Cite (ACL):
Mrinalini Luthra and Brecht Nijman. 2024. Lost in Translation? Approaches to Gender Representation in Multilingual Archives. In Proceedings of the 2nd International Workshop on Gender-Inclusive Translation Technologies, pages 42–55, Sheffield, United Kingdom. European Association for Machine Translation (EAMT).
Cite (Informal):
Lost in Translation? Approaches to Gender Representation in Multilingual Archives (Luthra & Nijman, GITT-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.gitt-1.5.pdf