@inproceedings{zhou-etal-2021-self,
title = "Self-Guided Curriculum Learning for Neural Machine Translation",
author = "Zhou, Lei and
Ding, Liang and
Duh, Kevin and
Watanabe, Shinji and
Sasano, Ryohei and
Takeda, Koichi",
editor = "Federico, Marcello and
Waibel, Alex and
Costa-juss{\`a}, Marta R. and
Niehues, Jan and
Stuker, Sebastian and
Salesky, Elizabeth",
booktitle = "Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)",
month = aug,
year = "2021",
address = "Bangkok, Thailand (online)",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.iwslt-1.25/",
doi = "10.18653/v1/2021.iwslt-1.25",
pages = "206--214",
abstract = "In supervised learning, a well-trained model should be able to recover ground truth accurately, i.e. the predicted labels are expected to resemble the ground truth labels as much as possible. Inspired by this, we formulate a difficulty criterion based on the recovery degrees of training examples. Motivated by the intuition that after skimming through the training corpus, the neural machine translation (NMT) model {\textquotedblleft}knows{\textquotedblright} how to schedule a suitable curriculum according to learning difficulty, we propose a self-guided curriculum learning strategy that encourages the NMT model to learn from easy to hard on the basis of recovery degrees. Specifically, we adopt sentence-level BLEU score as the proxy of recovery degree. Experimental results on translation benchmarks including WMT14 English-German and WMT17 Chinese-English demonstrate that our proposed method considerably improves the recovery degree, thus consistently improving the translation performance."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2021-self">
<titleInfo>
<title>Self-Guided Curriculum Learning for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liang</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shinji</namePart>
<namePart type="family">Watanabe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryohei</namePart>
<namePart type="family">Sasano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Koichi</namePart>
<namePart type="family">Takeda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marcello</namePart>
<namePart type="family">Federico</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alex</namePart>
<namePart type="family">Waibel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marta</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Costa-jussà</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Niehues</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Stuker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Salesky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand (online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In supervised learning, a well-trained model should be able to recover ground truth accurately, i.e. the predicted labels are expected to resemble the ground truth labels as much as possible. Inspired by this, we formulate a difficulty criterion based on the recovery degrees of training examples. Motivated by the intuition that after skimming through the training corpus, the neural machine translation (NMT) model “knows” how to schedule a suitable curriculum according to learning difficulty, we propose a self-guided curriculum learning strategy that encourages the NMT model to learn from easy to hard on the basis of recovery degrees. Specifically, we adopt sentence-level BLEU score as the proxy of recovery degree. Experimental results on translation benchmarks including WMT14 English-German and WMT17 Chinese-English demonstrate that our proposed method considerably improves the recovery degree, thus consistently improving the translation performance.</abstract>
<identifier type="citekey">zhou-etal-2021-self</identifier>
<identifier type="doi">10.18653/v1/2021.iwslt-1.25</identifier>
<location>
<url>https://aclanthology.org/2021.iwslt-1.25/</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>206</start>
<end>214</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Self-Guided Curriculum Learning for Neural Machine Translation
%A Zhou, Lei
%A Ding, Liang
%A Duh, Kevin
%A Watanabe, Shinji
%A Sasano, Ryohei
%A Takeda, Koichi
%Y Federico, Marcello
%Y Waibel, Alex
%Y Costa-jussà, Marta R.
%Y Niehues, Jan
%Y Stuker, Sebastian
%Y Salesky, Elizabeth
%S Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand (online)
%F zhou-etal-2021-self
%X In supervised learning, a well-trained model should be able to recover ground truth accurately, i.e. the predicted labels are expected to resemble the ground truth labels as much as possible. Inspired by this, we formulate a difficulty criterion based on the recovery degrees of training examples. Motivated by the intuition that after skimming through the training corpus, the neural machine translation (NMT) model “knows” how to schedule a suitable curriculum according to learning difficulty, we propose a self-guided curriculum learning strategy that encourages the NMT model to learn from easy to hard on the basis of recovery degrees. Specifically, we adopt sentence-level BLEU score as the proxy of recovery degree. Experimental results on translation benchmarks including WMT14 English-German and WMT17 Chinese-English demonstrate that our proposed method considerably improves the recovery degree, thus consistently improving the translation performance.
%R 10.18653/v1/2021.iwslt-1.25
%U https://aclanthology.org/2021.iwslt-1.25/
%U https://doi.org/10.18653/v1/2021.iwslt-1.25
%P 206-214
Markdown (Informal)
[Self-Guided Curriculum Learning for Neural Machine Translation](https://aclanthology.org/2021.iwslt-1.25/) (Zhou et al., IWSLT 2021)
ACL
- Lei Zhou, Liang Ding, Kevin Duh, Shinji Watanabe, Ryohei Sasano, and Koichi Takeda. 2021. Self-Guided Curriculum Learning for Neural Machine Translation. In Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021), pages 206–214, Bangkok, Thailand (online). Association for Computational Linguistics.