<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2020-multi">
    <titleInfo>
        <title>Multi-Reward based Reinforcement Learning for Neural Machine Translation</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Shuo</namePart>
        <namePart type="family">Sun</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Hongxu</namePart>
        <namePart type="family">Hou</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Nier</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Ziyue</namePart>
        <namePart type="family">Guo</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chaowei</namePart>
        <namePart type="family">Zhang</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-oct</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <language>
        <languageTerm type="text">English</languageTerm>
        <languageTerm type="code" authority="iso639-2b">eng</languageTerm>
    </language>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 19th Chinese National Conference on Computational Linguistics</title>
        </titleInfo>
        <originInfo>
            <publisher>Chinese Information Processing Society of China</publisher>
            <place>
                <placeTerm type="text">Haikou, China</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Reinforcement learning (RL) has made remarkable progress in neural machine translation (NMT). However, it exists the problems with uneven sampling distribution, sparse rewards and high variance in training phase. Therefore, we propose a multi-reward reinforcement learning training strategy to decouple action selection and value estimation. Meanwhile, our method combines with language model rewards to jointly optimize model parameters. In addition, we add Gumbel noise in sampling to obtain more effective semantic information. To verify the robustness of our method, we not only conducted experiments on large corpora, but also performed on low-resource languages. Experimental results show that our work is superior to the baselines in WMT14 English-German, LDC2014 Chinese-English and CWMT2018 Mongolian-Chinese tasks, which fully certificates the effectiveness of our method.</abstract>
    <identifier type="citekey">sun-etal-2020-multi</identifier>
    <location>
        <url>https://aclanthology.org/2020.ccl-1.91</url>
    </location>
    <part>
        <date>2020-oct</date>
        <extent unit="page">
            <start>984</start>
            <end>993</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Multi-Reward based Reinforcement Learning for Neural Machine Translation
%A Sun, Shuo
%A Hou, Hongxu
%A Wu, Nier
%A Guo, Ziyue
%A Zhang, Chaowei
%S Proceedings of the 19th Chinese National Conference on Computational Linguistics
%D 2020
%8 oct
%I Chinese Information Processing Society of China
%C Haikou, China
%G English
%F sun-etal-2020-multi
%X Reinforcement learning (RL) has made remarkable progress in neural machine translation (NMT). However, it exists the problems with uneven sampling distribution, sparse rewards and high variance in training phase. Therefore, we propose a multi-reward reinforcement learning training strategy to decouple action selection and value estimation. Meanwhile, our method combines with language model rewards to jointly optimize model parameters. In addition, we add Gumbel noise in sampling to obtain more effective semantic information. To verify the robustness of our method, we not only conducted experiments on large corpora, but also performed on low-resource languages. Experimental results show that our work is superior to the baselines in WMT14 English-German, LDC2014 Chinese-English and CWMT2018 Mongolian-Chinese tasks, which fully certificates the effectiveness of our method.
%U https://aclanthology.org/2020.ccl-1.91
%P 984-993

Markdown (Informal)

[Multi-Reward based Reinforcement Learning for Neural Machine Translation](https://aclanthology.org/2020.ccl-1.91) (Sun et al., CCL 2020)

• Multi-Reward based Reinforcement Learning for Neural Machine Translation (Sun et al., CCL 2020)

ACL

• Shuo Sun, Hongxu Hou, Nier Wu, Ziyue Guo, and Chaowei Zhang. 2020. Multi-Reward based Reinforcement Learning for Neural Machine Translation. In Proceedings of the 19th Chinese National Conference on Computational Linguistics, pages 984–993, Haikou, China. Chinese Information Processing Society of China.