Are Large Language Models State-of-the-art Quality Estimators for Machine Translation of User-generated Content?

S Qian, C Orăsan, D Kanojia, F Carmo - arxiv preprint arxiv:2410.06338, 2024 - arxiv.org
This paper investigates whether large language models (LLMs) are state-of-the-art quality
estimators for machine translation of user-generated content (UGC) that contains emotional …

A Multi-task Learning Framework for Evaluating Machine Translation of Emotion-loaded User-generated Content

S Qian, C Orăsan, D Kanojia, F Carmo - arxiv preprint arxiv:2410.03277, 2024 - arxiv.org
Machine translation (MT) of user-generated content (UGC) poses unique challenges,
including handling slang, emotion, and literary devices like irony and sarcasm. Evaluating …

Challenges of Human vs Machine Translation of Emotion-Loaded Chinese Microblog Texts

S Qian, C Orǎsan, F Do Carmo… - Proceedings of Machine …, 2023 - aclanthology.org
This paper attempts to identify challenges professional translators face when translating
emotion-loaded texts as well as errors machine translation (MT) makes when translating this …

Evaluating Machine Translation for Emotion-loaded User Generated Content (TransEval4Emo-UGC)

S Qian, C Orašan, F Do Carmo… - Proceedings of the 25th …, 2024 - aclanthology.org
Evaluating Machine Translation for Emotion-loaded User Generated Content (TransEval4Emo-UGC)
Page 1 Proceedings of the 25th Annual Conference of the European Association for Machine …