@inproceedings{menglong-yanliang-2024-simclnmt,
title = "{S}im{CLNMT}: A Simple Contrastive Learning Method for Enhancing Neural Machine Translation Quality",
author = "Menglong, Xu and
Yanliang, Zhang",
editor = "Sun, Maosong and
Liang, Jiye and
Han, Xianpei and
Liu, Zhiyuan and
He, Yulan",
booktitle = "Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)",
month = jul,
year = "2024",
address = "Taiyuan, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2024.ccl-1.81/",
pages = "1047--1058",
language = "eng",
abstract = "{\textquotedblleft}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{\textquotedblright}"
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="menglong-yanliang-2024-simclnmt">
<titleInfo>
<title>SimCLNMT: A Simple Contrastive Learning Method for Enhancing Neural Machine Translation Quality</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Menglong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhang</namePart>
<namePart type="family">Yanliang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiye</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianpei</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Taiyuan, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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”</abstract>
<identifier type="citekey">menglong-yanliang-2024-simclnmt</identifier>
<location>
<url>https://aclanthology.org/2024.ccl-1.81/</url>
</location>
<part>
<date>2024-07</date>
<extent unit="page">
<start>1047</start>
<end>1058</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SimCLNMT: A Simple Contrastive Learning Method for Enhancing Neural Machine Translation Quality
%A Menglong, Xu
%A Yanliang, Zhang
%Y Sun, Maosong
%Y Liang, Jiye
%Y Han, Xianpei
%Y Liu, Zhiyuan
%Y He, Yulan
%S Proceedings of the 23rd Chinese National Conference on Computational Linguistics (Volume 1: Main Conference)
%D 2024
%8 July
%I Chinese Information Processing Society of China
%C Taiyuan, China
%G eng
%F menglong-yanliang-2024-simclnmt
%X “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”
%U https://aclanthology.org/2024.ccl-1.81/
%P 1047-1058
Markdown (Informal)
[SimCLNMT: A Simple Contrastive Learning Method for Enhancing Neural Machine Translation Quality](https://aclanthology.org/2024.ccl-1.81/) (Menglong & Yanliang, CCL 2024)
ACL