Abstract
This paper describes SheffieldGATE’s submission to WMT 2024 Chat Shared Translation Task. We participate in three language pairs: English-German, English-Dutch, and English-Portuguese (Brazil). In this work, we introduce a context-aware sliding window decoding method to track dependencies between chat messages. We fine-tune a large pre-trained language model based on the training data provided by the shared task Our experiments (i) compare the model performance between multilingual and bilingual fine-tuning and (ii) assess the impact of different window sizes. Our experimental results demonstrate that utilising contextual information yields superior performance in document-level translation compared to translating documents as isolated text segments, and that models fine-tuned with multilingual data perform better than those fine-tuned with bilingual data.- Anthology ID:
- 2024.wmt-1.101
- 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:
- 1004–1010
- Language:
- URL:
- https://aclanthology.org/2024.wmt-1.101
- DOI:
- 10.18653/v1/2024.wmt-1.101
- Cite (ACL):
- Xinye Yang, Yida Mu, Kalina Bontcheva, and Xingyi Song. 2024. Optimising LLM-Driven Machine Translation with Context-Aware Sliding Windows. In Proceedings of the Ninth Conference on Machine Translation, pages 1004–1010, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- Optimising LLM-Driven Machine Translation with Context-Aware Sliding Windows (Yang et al., WMT 2024)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2024.wmt-1.101.pdf