Akal Badi ya Bias: An Exploratory Study of Gender Bias in Hindi Language Technology

R Hada, S Husain, V Gumma, H Diddee… - The 2024 ACM …, 2024 - dl.acm.org
Existing research in measuring and mitigating gender bias predominantly centers on
English, overlooking the intricate challenges posed by non-English languages and the …

An image speaks a thousand words, but can everyone listen? On translating images for cultural relevance

S Khanuja, S Ramamoorthy, Y Song… - arXiv preprint arXiv …, 2024 - arxiv.org
Given the rise of multimedia content, human translators increasingly focus on culturally
adapting not only words but also other modalities such as images to convey the same …

Improving LLM abilities in idiomatic translation

S Donthi, M Spencer, O Patel, J Doh… - arXiv preprint arXiv …, 2024 - arxiv.org
For large language models (LLMs) like NLLB and GPT, translating idioms remains a
challenge. Our goal is to enhance translation fidelity by improving LLM processing of …

Enhancing Idiomatic Representation in Multiple Languages via an Adaptive Contrastive Triplet Loss

W He, M Idiart, C Scarton, A Villavicencio - arXiv preprint arXiv …, 2024 - arxiv.org
Accurately modeling idiomatic or non-compositional language has been a longstanding
challenge in Natural Language Processing (NLP). This is partly because these expressions …

[PDF][PDF] From Neural Machine Translation to Large Language Models: Analysing Translation Quality of Chinese Idioms

Y Zhu, DM Lal, S Denysiuk, R Mitkov - acl-bg.org
Idioms present a formidable challenge for machine translation (MT) due to their figurative,
culture-specific, and linguistic complexity. In this study, we compiled a corpus of 100 …