SimCLNMT: A Simple Contrastive Learning Method for Enhancing Neural Machine Translation Quality

Xu Menglong, Zhang Yanliang


Abstract
“Neural Machine Translation (NMT) models are typically trained using Maximum LikelihoodEstimation (MLE). However, this approach has a limitation: while it might select the bestword for the immediate context, it does not generally optimize for the entire sentence. Tomitigate this issue, we propose a simple yet effective training method called SimCLNMT.This method is designed to select words that fit well in the immediate context and also en-hance the overall translation quality over time. During training, SimCLNMT scores multiplesystem-generated (candidate) translations using the logarithm of conditional probabilities.Itthen employs a ranking loss function to learn and adjust these probabilities to align with thecorresponding quality scores. Our experimental results demonstrate that SimCLNMT consis-tently outperforms traditional MLE training on both the NIST English-Chinese and WMT’14English-German datasets. Further analysis also indicates that the translations generated by ourmodel are more closely aligned with the corresponding quality scores. We release our code athttps://github.com/chaos130/fairseq_SimCLNMT.Introduction”
Anthology ID:
2024.ccl-1.81
Volume:
Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)
Month:
July
Year:
2024
Address:
Taiyuan, China
Editors:
Maosong Sun, Jiye Liang, Xianpei Han, Zhiyuan Liu, Yulan He
Venue:
CCL
SIG:
Publisher:
Chinese Information Processing Society of China
Note:
Pages:
1047–1058
Language:
English
URL:
https://aclanthology.org/2024.ccl-1.81/
DOI:
Bibkey:
Cite (ACL):
Xu Menglong and Zhang Yanliang. 2024. SimCLNMT: A Simple Contrastive Learning Method for Enhancing Neural Machine Translation Quality. In Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference), pages 1047–1058, Taiyuan, China. Chinese Information Processing Society of China.
Cite (Informal):
SimCLNMT: A Simple Contrastive Learning Method for Enhancing Neural Machine Translation Quality (Menglong & Yanliang, CCL 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.ccl-1.81.pdf