Abstract
Decoder-only large language models (LLMs) have recently demonstrated impressive capabilities in text generation and reasoning. Nonetheless, they have limited applications in simultaneous machine translation (SiMT), currently dominated by encoder-decoder transformers. This study demonstrates that, after fine-tuning on a small dataset comprising causally aligned source and target sentence pairs, a pre-trained open-source LLM can control input segmentation directly by generating a special “wait” token. This obviates the need for a separate policy and enables the LLM to perform English-German and English-Russian SiMT tasks with BLEU scores that are comparable to those of specific state-of-the-art baselines. We also evaluated closed-source models such as GPT-4, which displayed encouraging results in performing the SiMT task without prior training (zero-shot), indicating a promising avenue for enhancing future SiMT systems.- Anthology ID:
- 2024.findings-emnlp.27
- Volume:
- Findings of the Association for Computational Linguistics: EMNLP 2024
- Month:
- November
- Year:
- 2024
- Address:
- Miami, Florida, USA
- Editors:
- Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
- Venue:
- Findings
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 461–476
- Language:
- URL:
- https://aclanthology.org/2024.findings-emnlp.27
- DOI:
- 10.18653/v1/2024.findings-emnlp.27
- Cite (ACL):
- Roman Koshkin, Katsuhito Sudoh, and Satoshi Nakamura. 2024. TransLLaMa: LLM-based Simultaneous Translation System. In Findings of the Association for Computational Linguistics: EMNLP 2024, pages 461–476, Miami, Florida, USA. Association for Computational Linguistics.
- Cite (Informal):
- TransLLaMa: LLM-based Simultaneous Translation System (Koshkin et al., Findings 2024)
- PDF:
- https://preview.aclanthology.org/dois-2013-emnlp/2024.findings-emnlp.27.pdf