Simultaneous Machine Translation with Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917085006790656 |
|---|---|
| author | Wang, Minghan Zhao, Jinming Vu, Thuy-Trang Shiri, Fatemeh Shareghi, Ehsan Haffari, Gholamreza |
| author_facet | Wang, Minghan Zhao, Jinming Vu, Thuy-Trang Shiri, Fatemeh Shareghi, Ehsan Haffari, Gholamreza |
| contents | Real-world simultaneous machine translation (SimulMT) systems face more challenges than just the quality-latency trade-off. They also need to address issues related to robustness with noisy input, processing long contexts, and flexibility for knowledge injection. These challenges demand models with strong language understanding and generation capabilities which may not often equipped by dedicated MT models. In this paper, we investigate the possibility of applying Large Language Models (LLM) to SimulMT tasks by using existing incremental-decoding methods with a newly proposed RALCP algorithm for latency reduction. We conducted experiments using the \texttt{Llama2-7b-chat} model on nine different languages from the MUST-C dataset. The results show that LLM outperforms dedicated MT models in terms of BLEU and LAAL metrics. Further analysis indicates that LLM has advantages in terms of tuning efficiency and robustness. However, it is important to note that the computational cost of LLM remains a significant obstacle to its application in SimulMT. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_06706 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Simultaneous Machine Translation with Large Language Models Wang, Minghan Zhao, Jinming Vu, Thuy-Trang Shiri, Fatemeh Shareghi, Ehsan Haffari, Gholamreza Computation and Language Real-world simultaneous machine translation (SimulMT) systems face more challenges than just the quality-latency trade-off. They also need to address issues related to robustness with noisy input, processing long contexts, and flexibility for knowledge injection. These challenges demand models with strong language understanding and generation capabilities which may not often equipped by dedicated MT models. In this paper, we investigate the possibility of applying Large Language Models (LLM) to SimulMT tasks by using existing incremental-decoding methods with a newly proposed RALCP algorithm for latency reduction. We conducted experiments using the \texttt{Llama2-7b-chat} model on nine different languages from the MUST-C dataset. The results show that LLM outperforms dedicated MT models in terms of BLEU and LAAL metrics. Further analysis indicates that LLM has advantages in terms of tuning efficiency and robustness. However, it is important to note that the computational cost of LLM remains a significant obstacle to its application in SimulMT. |
| title | Simultaneous Machine Translation with Large Language Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2309.06706 |