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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Yang, Jinlong, Shang, Hengchao, Wei, Daimeng, Guo, Jiaxin, Li, Zongyao, Wu, Zhanglin, Rao, Zhiqiang, Li, Shaojun, Xie, Yuhao, Luo, Yuanchang, Zheng, Jiawei, Wei, Bin, Yang, Hao
Format: Preprint
Veröffentlicht: 2024
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916410601504768
author Yang, Jinlong
Shang, Hengchao
Wei, Daimeng
Guo, Jiaxin
Li, Zongyao
Wu, Zhanglin
Rao, Zhiqiang
Li, Shaojun
Xie, Yuhao
Luo, Yuanchang
Zheng, Jiawei
Wei, Bin
Yang, Hao
author_facet Yang, Jinlong
Shang, Hengchao
Wei, Daimeng
Guo, Jiaxin
Li, Zongyao
Wu, Zhanglin
Rao, Zhiqiang
Li, Shaojun
Xie, Yuhao
Luo, Yuanchang
Zheng, Jiawei
Wei, Bin
Yang, Hao
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2409_16331
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Exploring the traditional NMT model and Large Language Model for chat translation
Yang, Jinlong
Shang, Hengchao
Wei, Daimeng
Guo, Jiaxin
Li, Zongyao
Wu, Zhanglin
Rao, Zhiqiang
Li, Shaojun
Xie, Yuhao
Luo, Yuanchang
Zheng, Jiawei
Wei, Bin
Yang, Hao
Computation and Language
Artificial Intelligence
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.
title Exploring the traditional NMT model and Large Language Model for chat translation
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2409.16331