Summary of Exploring the Traditional Nmt Model and Large Language Model For Chat Translation, by Jinlong Yang et al.
Exploring the traditional NMT model and Large Language Model for chat translation
by Jinlong Yang, Hengchao Shang, Daimeng Wei, Jiaxin Guo, Zongyao Li, Zhanglin Wu, Zhiqiang Rao, Shaojun Li, Yuhao Xie, Yuanchang Luo, Jiawei Zheng, Bin Wei, Hao Yang
First submitted to arxiv on: 24 Sep 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Artificial Intelligence (cs.AI)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary This paper presents Huawei Translation Services Center’s submissions to the WMT24 chat translation shared task on English-German (en-de) bidirectional translation. The team fine-tuned models using chat data, exploring methods like Minimum Bayesian Risk (MBR) decoding and self-training. Results show significant performance improvements in certain directions, with the MBR self-training method achieving the best results. The Large Language Model also highlights challenges and potential research avenues in chat translation. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about a team that tried to improve machine translation for chatting between English and German speakers. They used special training data and different techniques to make their models better. They got some great results, especially when they used something called Minimum Bayesian Risk decoding. The team also talks about the challenges they faced and what they think other researchers should focus on in the future. |
Keywords
» Artificial intelligence » Large language model » Self training » Translation
