<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-etal-2020-generating">
    <titleInfo>
        <title>Generating Diverse Translation from Model Distribution with Dropout</title>
    </titleInfo>
    <name type="personal">
        <namePart type="given">Xuanfu</namePart>
        <namePart type="family">Wu</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Yang</namePart>
        <namePart type="family">Feng</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <name type="personal">
        <namePart type="given">Chenze</namePart>
        <namePart type="family">Shao</namePart>
        <role>
            <roleTerm authority="marcrelator" type="text">author</roleTerm>
        </role>
    </name>
    <originInfo>
        <dateIssued>2020-11</dateIssued>
    </originInfo>
    <typeOfResource>text</typeOfResource>
    <relatedItem type="host">
        <titleInfo>
            <title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
        </titleInfo>
        <name type="personal">
            <namePart type="given">Bonnie</namePart>
            <namePart type="family">Webber</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <name type="personal">
            <namePart type="given">Trevor</namePart>
            <namePart type="family">Cohn</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>
        <name type="personal">
            <namePart type="given">Yang</namePart>
            <namePart type="family">Liu</namePart>
            <role>
                <roleTerm authority="marcrelator" type="text">editor</roleTerm>
            </role>
        </name>
        <originInfo>
            <publisher>Association for Computational Linguistics</publisher>
            <place>
                <placeTerm type="text">Online</placeTerm>
            </place>
        </originInfo>
        <genre authority="marcgt">conference publication</genre>
    </relatedItem>
    <abstract>Despite the improvement of translation quality, neural machine translation (NMT) often suffers from the lack of diversity in its generation. In this paper, we propose to generate diverse translations by deriving a large number of possible models with Bayesian modelling and sampling models from them for inference. The possible models are obtained by applying concrete dropout to the NMT model and each of them has specific confidence for its prediction, which corresponds to a posterior model distribution under specific training data in the principle of Bayesian modeling. With variational inference, the posterior model distribution can be approximated with a variational distribution, from which the final models for inference are sampled. We conducted experiments on Chinese-English and English-German translation tasks and the results shows that our method makes a better trade-off between diversity and accuracy.</abstract>
    <identifier type="citekey">wu-etal-2020-generating</identifier>
    <identifier type="doi">10.18653/v1/2020.emnlp-main.82</identifier>
    <location>
        <url>https://aclanthology.org/2020.emnlp-main.82</url>
    </location>
    <part>
        <date>2020-11</date>
        <extent unit="page">
            <start>1088</start>
            <end>1097</end>
        </extent>
    </part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Generating Diverse Translation from Model Distribution with Dropout
%A Wu, Xuanfu
%A Feng, Yang
%A Shao, Chenze
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F wu-etal-2020-generating
%X Despite the improvement of translation quality, neural machine translation (NMT) often suffers from the lack of diversity in its generation. In this paper, we propose to generate diverse translations by deriving a large number of possible models with Bayesian modelling and sampling models from them for inference. The possible models are obtained by applying concrete dropout to the NMT model and each of them has specific confidence for its prediction, which corresponds to a posterior model distribution under specific training data in the principle of Bayesian modeling. With variational inference, the posterior model distribution can be approximated with a variational distribution, from which the final models for inference are sampled. We conducted experiments on Chinese-English and English-German translation tasks and the results shows that our method makes a better trade-off between diversity and accuracy.
%R 10.18653/v1/2020.emnlp-main.82
%U https://aclanthology.org/2020.emnlp-main.82
%U https://doi.org/10.18653/v1/2020.emnlp-main.82
%P 1088-1097

Markdown (Informal)

[Generating Diverse Translation from Model Distribution with Dropout](https://aclanthology.org/2020.emnlp-main.82) (Wu et al., EMNLP 2020)

• Generating Diverse Translation from Model Distribution with Dropout (Wu et al., EMNLP 2020)

ACL

• Xuanfu Wu, Yang Feng, and Chenze Shao. 2020. Generating Diverse Translation from Model Distribution with Dropout. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 1088–1097, Online. Association for Computational Linguistics.