Enhancing Gender-Inclusive Machine Translation with Neomorphemes and Large Language Models
Machine translation (MT) models are known to suffer from gender bias, especially when
translating into languages with extensive gendered morphology. Accordingly, they still fall …
translating into languages with extensive gendered morphology. Accordingly, they still fall …
The power of Prompts: Evaluating and Mitigating Gender Bias in MT with LLMs
A Sant, C Escolano, A Mash, FDL Fornaciari… - arXiv preprint arXiv …, 2024 - arxiv.org
This paper studies gender bias in machine translation through the lens of Large Language
Models (LLMs). Four widely-used test sets are employed to benchmark various base LLMs …
Models (LLMs). Four widely-used test sets are employed to benchmark various base LLMs …
[PDF][PDF] Automatic detection of (potential) factors in the source text leading to gender bias in machine translation
J Hackenbuchner, A Tezcan… - Proceedings of the 24th …, 2024 - backoffice.biblio.ugent.be
This research project aims to develop a comprehensive methodology to help make machine
translation (MT) systems more gender-inclusive for society. The goal is the creation of a …
translation (MT) systems more gender-inclusive for society. The goal is the creation of a …
You Shall Know a Word's Gender by the Company it Keeps: Comparing the Role of Context in Human Gender Assumptions with MT
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 …
their gender translations and associations on role names and on stereotypicality in the …
[PDF][PDF] Innovations and Challenges in Neural Machine Translation: A Review
M Ashraf - researchgate.net
Neural Machine Translation NMT has revolutionized language translation through the use of
deep learning techniques that offer greater accuracy and contextual understanding …
deep learning techniques that offer greater accuracy and contextual understanding …