# Exploring the traditional NMT model and Large Language Model for chat translation

arXiv: https://arxiv.org/abs/2409.16331 · HTML: https://mlsanity.com/paper/2409.16331/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 25 references that are in the map.
- First posted on arXiv 24 Sep 2024.

## Builds on (most cited first, 14 of 14)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Neural Machine Translation by Jointly Learning to Align and Translate](https://mlsanity.com/paper/1409.0473/) (2014)
- [Sequence to Sequence Learning with Neural Networks](https://mlsanity.com/paper/1409.3215/) (2014)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [Convolutional Sequence to Sequence Learning](https://mlsanity.com/paper/1705.03122/) (2017)
- [Beam Search Strategies for Neural Machine Translation](https://mlsanity.com/paper/1702.01806/) (2017)
- [R-Drop: Regularized Dropout for Neural Networks](https://mlsanity.com/paper/2106.14448/) (2021)
- [Document-Level Machine Translation with Large Language Models](https://mlsanity.com/paper/2304.02210/) (2023)
- [Tagged Back-Translation](https://mlsanity.com/paper/1906.06442/) (2019)
- [Adapting Large Language Models for Document-Level Machine Translation](https://mlsanity.com/paper/2401.06468/) (2024)
- [Exploiting Deep Representations for Neural Machine Translation](https://mlsanity.com/paper/1810.10181/) (2018)
- [Generalizing Back-Translation in Neural Machine Translation](https://mlsanity.com/paper/1906.07286/) (2019)
- [Model-Based Minimum Bayes Risk Decoding for Text Generation](https://mlsanity.com/paper/2311.05263/) (2023)

## Abstract (arXiv)

This paper describes the submissions of Huawei Translation Services Center(HW-TSC) to WMT24 chat translation shared task on EnglishleftrightarrowGermany (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.