Exploring the traditional NMT model and Large Language Model for chat translation
This work addresses chat translation for users needing real-time communication, but it is incremental as it applies existing methods to a specific shared task.
This paper tackled chat translation between English and German by fine-tuning models with chat data and exploring strategies like Minimum Bayesian Risk decoding and self-training, achieving significant performance improvements in certain directions with the MBR self-training method yielding the best results.
This paper describes the submissions of Huawei Translation Services Center(HW-TSC) to WMT24 chat translation shared task on English$\leftrightarrow$Germany (en-de) bidirection. The experiments involved fine-tuning models using chat data and exploring various strategies, including Minimum Bayesian Risk (MBR) decoding and self-training. The results show significant performance improvements in certain directions, with the MBR self-training method achieving the best results. The Large Language Model also discusses the challenges and potential avenues for further research in the field of chat translation.