Simultaneous Machine Translation with Large Language Models
This work addresses real-world simultaneous translation issues like robustness and flexibility for practitioners, but it is incremental as it adapts existing methods to LLMs.
The paper tackles simultaneous machine translation challenges by applying Large Language Models with a new RALCP algorithm for latency reduction, showing that LLMs outperform dedicated MT models in BLEU and LAAL metrics on nine languages from the MUST-C dataset.
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.