Abstract
The rapid growth of deep learning has spurred significant advancements across industries, par- ticularly in machine translation through large language models (LLMs). However, translat- ing literary still presents challenges, including cross-cultural nuances, complex language struc- tures, metaphorical expressions, and cultural differences. To address these issues, this study utilizes the Llama and Phi models using both LoRA and full-parameter techniques, along-side a prompt-based translation system. Full-parameter tuning of the Llama-3-Chinese-8B-Instruct model was unsuccessful due to mem-ory constraints. In terms of the WMT task, the fully fine-tuned Phi 3 model was selected for submission due to its more natural and flu-ent translations. Nonetheless, results showed that LoRA and the prompt-based system sig- nificantly improved the Llama3 model’s perfor- mance, surpassing other models in BLEU and ROUGE evaluations.- Anthology ID:
- 2024.wmt-1.99
- 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:
- 987–992
- Language:
- URL:
- https://preview.aclanthology.org/add_missing_videos/2024.wmt-1.99/
- DOI:
- 10.18653/v1/2024.wmt-1.99
- Cite (ACL):
- Kechen Li, Yaotian Tao, Hongyi Huang, and Tianbo Ji. 2024. LinChance-NTU for Unconstrained WMT2024 Literary Translation. In Proceedings of the Ninth Conference on Machine Translation, pages 987–992, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- LinChance-NTU for Unconstrained WMT2024 Literary Translation (Li et al., WMT 2024)
- PDF:
- https://preview.aclanthology.org/add_missing_videos/2024.wmt-1.99.pdf