@inproceedings{li-etal-2019-understanding,
title = "Understanding Data Augmentation in Neural Machine Translation: Two Perspectives towards Generalization",
author = "Li, Guanlin and
Liu, Lemao and
Huang, Guoping and
Zhu, Conghui and
Zhao, Tiejun",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1570/",
doi = "10.18653/v1/D19-1570",
pages = "5689--5695",
abstract = "Many Data Augmentation (DA) methods have been proposed for neural machine translation. Existing works measure the superiority of DA methods in terms of their performance on a specific test set, but we find that some DA methods do not exhibit consistent improvements across translation tasks. Based on the observation, this paper makes an initial attempt to answer a fundamental question: what benefits, which are consistent across different methods and tasks, does DA in general obtain? Inspired by recent theoretic advances in deep learning, the paper understands DA from two perspectives towards the generalization ability of a model: input sensitivity and prediction margin, which are defined independent of specific test set thereby may lead to findings with relatively low variance. Extensive experiments show that relatively consistent benefits across five DA methods and four translation tasks are achieved regarding both perspectives."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2019-understanding">
<titleInfo>
<title>Understanding Data Augmentation in Neural Machine Translation: Two Perspectives towards Generalization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guanlin</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lemao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guoping</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Conghui</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tiejun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Many Data Augmentation (DA) methods have been proposed for neural machine translation. Existing works measure the superiority of DA methods in terms of their performance on a specific test set, but we find that some DA methods do not exhibit consistent improvements across translation tasks. Based on the observation, this paper makes an initial attempt to answer a fundamental question: what benefits, which are consistent across different methods and tasks, does DA in general obtain? Inspired by recent theoretic advances in deep learning, the paper understands DA from two perspectives towards the generalization ability of a model: input sensitivity and prediction margin, which are defined independent of specific test set thereby may lead to findings with relatively low variance. Extensive experiments show that relatively consistent benefits across five DA methods and four translation tasks are achieved regarding both perspectives.</abstract>
<identifier type="citekey">li-etal-2019-understanding</identifier>
<identifier type="doi">10.18653/v1/D19-1570</identifier>
<location>
<url>https://aclanthology.org/D19-1570/</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>5689</start>
<end>5695</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Understanding Data Augmentation in Neural Machine Translation: Two Perspectives towards Generalization
%A Li, Guanlin
%A Liu, Lemao
%A Huang, Guoping
%A Zhu, Conghui
%A Zhao, Tiejun
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F li-etal-2019-understanding
%X Many Data Augmentation (DA) methods have been proposed for neural machine translation. Existing works measure the superiority of DA methods in terms of their performance on a specific test set, but we find that some DA methods do not exhibit consistent improvements across translation tasks. Based on the observation, this paper makes an initial attempt to answer a fundamental question: what benefits, which are consistent across different methods and tasks, does DA in general obtain? Inspired by recent theoretic advances in deep learning, the paper understands DA from two perspectives towards the generalization ability of a model: input sensitivity and prediction margin, which are defined independent of specific test set thereby may lead to findings with relatively low variance. Extensive experiments show that relatively consistent benefits across five DA methods and four translation tasks are achieved regarding both perspectives.
%R 10.18653/v1/D19-1570
%U https://aclanthology.org/D19-1570/
%U https://doi.org/10.18653/v1/D19-1570
%P 5689-5695
Markdown (Informal)
[Understanding Data Augmentation in Neural Machine Translation: Two Perspectives towards Generalization](https://aclanthology.org/D19-1570/) (Li et al., EMNLP-IJCNLP 2019)
ACL