Implementing Gender-Inclusivity in MT Output using Automatic Post-Editing with LLMs

Mara Nunziatini, Sara Diego


Abstract
This paper investigates the effectiveness of combining machine translation (MT) systems and large language models (LLMs) to produce gender-inclusive translations from English to Spanish. The study uses a multi-step approach where a translation is first generated by an MT engine and then reviewed by an LLM. The results suggest that while LLMs, particularly GPT-4, are successful in generating gender-inclusive post-edited translations and show potential in enhancing fluency, they often introduce unnecessary changes and inconsistencies. The findings underscore the continued necessity for human review in the translation process, highlighting the current limitations of AI systems in handling nuanced tasks like gender-inclusive translation. Also, the study highlights that while the combined approach can improve translation fluency, the effectiveness and reliability of the post-edited translations can vary based on the language of the prompts used.
Anthology ID:
2024.eamt-1.48
Volume:
Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1)
Month:
June
Year:
2024
Address:
Sheffield, UK
Editors:
Carolina Scarton, Charlotte Prescott, Chris Bayliss, Chris Oakley, Joanna Wright, Stuart Wrigley, Xingyi Song, Edward Gow-Smith, Rachel Bawden, Víctor M Sánchez-Cartagena, Patrick Cadwell, Ekaterina Lapshinova-Koltunski, Vera Cabarrão, Konstantinos Chatzitheodorou, Mary Nurminen, Diptesh Kanojia, Helena Moniz
Venue:
EAMT
SIG:
Publisher:
European Association for Machine Translation (EAMT)
Note:
Pages:
580–589
Language:
URL:
https://aclanthology.org/2024.eamt-1.48
DOI:
Bibkey:
Cite (ACL):
Mara Nunziatini and Sara Diego. 2024. Implementing Gender-Inclusivity in MT Output using Automatic Post-Editing with LLMs. In Proceedings of the 25th Annual Conference of the European Association for Machine Translation (Volume 1), pages 580–589, Sheffield, UK. European Association for Machine Translation (EAMT).
Cite (Informal):
Implementing Gender-Inclusivity in MT Output using Automatic Post-Editing with LLMs (Nunziatini & Diego, EAMT 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.eamt-1.48.pdf