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

Shenbin Qian, Constantin Orasan, Diptesh Kanojia, Félix Do Carmo


Abstract
Machine translation (MT) of user-generated content (UGC) poses unique challenges, including handling slang, emotion, and literary devices like irony and sarcasm. Evaluating the quality of these translations is challenging as current metrics do not focus on these ubiquitous features of UGC. To address this issue, we utilize an existing emotion-related dataset that includes emotion labels and human-annotated translation errors based on Multi-dimensional Quality Metrics. We extend it with sentence-level evaluation scores and word-level labels, leading to a dataset suitable for sentence- and word-level translation evaluation and emotion classification, in a multi-task setting. We propose a new architecture to perform these tasks concurrently, with a novel combined loss function, which integrates different loss heuristics, like the Nash and Aligned losses. Our evaluation compares existing fine-tuning and multi-task learning approaches, assessing generalization with ablative experiments over multiple datasets. Our approach achieves state-of-the-art performance and we present a comprehensive analysis for MT evaluation of UGC.
Anthology ID:
2024.wmt-1.113
Volume:
Proceedings of the Ninth Conference on Machine Translation
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Barry Haddow, Tom Kocmi, Philipp Koehn, Christof Monz
Venue:
WMT
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1140–1154
Language:
URL:
https://aclanthology.org/2024.wmt-1.113
DOI:
Bibkey:
Cite (ACL):
Shenbin Qian, Constantin Orasan, Diptesh Kanojia, and Félix Do Carmo. 2024. A Multi-task Learning Framework for Evaluating Machine Translation of Emotion-loaded User-generated Content. In Proceedings of the Ninth Conference on Machine Translation, pages 1140–1154, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
A Multi-task Learning Framework for Evaluating Machine Translation of Emotion-loaded User-generated Content (Qian et al., WMT 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.wmt-1.113.pdf