@inproceedings{graca-etal-2019-generalizing,
title = "Generalizing Back-Translation in Neural Machine Translation",
author = "Gra{\c{c}}a, Miguel and
Kim, Yunsu and
Schamper, Julian and
Khadivi, Shahram and
Ney, Hermann",
booktitle = "Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers)",
month = aug,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-5205",
doi = "10.18653/v1/W19-5205",
pages = "45--52",
abstract = "Back-translation {---} data augmentation by translating target monolingual data {---} is a crucial component in modern neural machine translation (NMT). In this work, we reformulate back-translation in the scope of cross-entropy optimization of an NMT model, clarifying its underlying mathematical assumptions and approximations beyond its heuristic usage. Our formulation covers broader synthetic data generation schemes, including sampling from a target-to-source NMT model. With this formulation, we point out fundamental problems of the sampling-based approaches and propose to remedy them by (i) disabling label smoothing for the target-to-source model and (ii) sampling from a restricted search space. Our statements are investigated on the WMT 2018 German {\textless}-{\textgreater} English news translation task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="graca-etal-2019-generalizing">
<titleInfo>
<title>Generalizing Back-Translation in Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="family">Graça</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunsu</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julian</namePart>
<namePart type="family">Schamper</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shahram</namePart>
<namePart type="family">Khadivi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hermann</namePart>
<namePart type="family">Ney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-aug</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Back-translation — data augmentation by translating target monolingual data — is a crucial component in modern neural machine translation (NMT). In this work, we reformulate back-translation in the scope of cross-entropy optimization of an NMT model, clarifying its underlying mathematical assumptions and approximations beyond its heuristic usage. Our formulation covers broader synthetic data generation schemes, including sampling from a target-to-source NMT model. With this formulation, we point out fundamental problems of the sampling-based approaches and propose to remedy them by (i) disabling label smoothing for the target-to-source model and (ii) sampling from a restricted search space. Our statements are investigated on the WMT 2018 German \textless-\textgreater English news translation task.</abstract>
<identifier type="citekey">graca-etal-2019-generalizing</identifier>
<identifier type="doi">10.18653/v1/W19-5205</identifier>
<location>
<url>https://aclanthology.org/W19-5205</url>
</location>
<part>
<date>2019-aug</date>
<extent unit="page">
<start>45</start>
<end>52</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Generalizing Back-Translation in Neural Machine Translation
%A Graça, Miguel
%A Kim, Yunsu
%A Schamper, Julian
%A Khadivi, Shahram
%A Ney, Hermann
%S Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers)
%D 2019
%8 aug
%I Association for Computational Linguistics
%C Florence, Italy
%F graca-etal-2019-generalizing
%X Back-translation — data augmentation by translating target monolingual data — is a crucial component in modern neural machine translation (NMT). In this work, we reformulate back-translation in the scope of cross-entropy optimization of an NMT model, clarifying its underlying mathematical assumptions and approximations beyond its heuristic usage. Our formulation covers broader synthetic data generation schemes, including sampling from a target-to-source NMT model. With this formulation, we point out fundamental problems of the sampling-based approaches and propose to remedy them by (i) disabling label smoothing for the target-to-source model and (ii) sampling from a restricted search space. Our statements are investigated on the WMT 2018 German \textless-\textgreater English news translation task.
%R 10.18653/v1/W19-5205
%U https://aclanthology.org/W19-5205
%U https://doi.org/10.18653/v1/W19-5205
%P 45-52
Markdown (Informal)
[Generalizing Back-Translation in Neural Machine Translation](https://aclanthology.org/W19-5205) (Graça et al., 2019)
ACL
- Miguel Graça, Yunsu Kim, Julian Schamper, Shahram Khadivi, and Hermann Ney. 2019. Generalizing Back-Translation in Neural Machine Translation. In Proceedings of the Fourth Conference on Machine Translation (Volume 1: Research Papers), pages 45–52, Florence, Italy. Association for Computational Linguistics.