@inproceedings{wei-etal-2019-online,
title = "Online Distilling from Checkpoints for Neural Machine Translation",
author = "Wei, Hao-Ran and
Huang, Shujian and
Wang, Ran and
Dai, Xin-yu and
Chen, Jiajun",
editor = "Burstein, Jill and
Doran, Christy and
Solorio, Thamar",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-1192",
doi = "10.18653/v1/N19-1192",
pages = "1932--1941",
abstract = "Current predominant neural machine translation (NMT) models often have a deep structure with large amounts of parameters, making these models hard to train and easily suffering from over-fitting. A common practice is to utilize a validation set to evaluate the training process and select the best checkpoint. Average and ensemble techniques on checkpoints can lead to further performance improvement. However, as these methods do not affect the training process, the system performance is restricted to the checkpoints generated in original training procedure. In contrast, we propose an online knowledge distillation method. Our method on-the-fly generates a teacher model from checkpoints, guiding the training process to obtain better performance. Experiments on several datasets and language pairs show steady improvement over a strong self-attention-based baseline system. We also provide analysis on data-limited setting against over-fitting. Furthermore, our method leads to an improvement in a machine reading experiment as well.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wei-etal-2019-online">
<titleInfo>
<title>Online Distilling from Checkpoints for Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hao-Ran</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shujian</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ran</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin-yu</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christy</namePart>
<namePart type="family">Doran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thamar</namePart>
<namePart type="family">Solorio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Current predominant neural machine translation (NMT) models often have a deep structure with large amounts of parameters, making these models hard to train and easily suffering from over-fitting. A common practice is to utilize a validation set to evaluate the training process and select the best checkpoint. Average and ensemble techniques on checkpoints can lead to further performance improvement. However, as these methods do not affect the training process, the system performance is restricted to the checkpoints generated in original training procedure. In contrast, we propose an online knowledge distillation method. Our method on-the-fly generates a teacher model from checkpoints, guiding the training process to obtain better performance. Experiments on several datasets and language pairs show steady improvement over a strong self-attention-based baseline system. We also provide analysis on data-limited setting against over-fitting. Furthermore, our method leads to an improvement in a machine reading experiment as well.</abstract>
<identifier type="citekey">wei-etal-2019-online</identifier>
<identifier type="doi">10.18653/v1/N19-1192</identifier>
<location>
<url>https://aclanthology.org/N19-1192</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>1932</start>
<end>1941</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Online Distilling from Checkpoints for Neural Machine Translation
%A Wei, Hao-Ran
%A Huang, Shujian
%A Wang, Ran
%A Dai, Xin-yu
%A Chen, Jiajun
%Y Burstein, Jill
%Y Doran, Christy
%Y Solorio, Thamar
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F wei-etal-2019-online
%X Current predominant neural machine translation (NMT) models often have a deep structure with large amounts of parameters, making these models hard to train and easily suffering from over-fitting. A common practice is to utilize a validation set to evaluate the training process and select the best checkpoint. Average and ensemble techniques on checkpoints can lead to further performance improvement. However, as these methods do not affect the training process, the system performance is restricted to the checkpoints generated in original training procedure. In contrast, we propose an online knowledge distillation method. Our method on-the-fly generates a teacher model from checkpoints, guiding the training process to obtain better performance. Experiments on several datasets and language pairs show steady improvement over a strong self-attention-based baseline system. We also provide analysis on data-limited setting against over-fitting. Furthermore, our method leads to an improvement in a machine reading experiment as well.
%R 10.18653/v1/N19-1192
%U https://aclanthology.org/N19-1192
%U https://doi.org/10.18653/v1/N19-1192
%P 1932-1941
Markdown (Informal)
[Online Distilling from Checkpoints for Neural Machine Translation](https://aclanthology.org/N19-1192) (Wei et al., NAACL 2019)
ACL
- Hao-Ran Wei, Shujian Huang, Ran Wang, Xin-yu Dai, and Jiajun Chen. 2019. Online Distilling from Checkpoints for Neural Machine Translation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1932–1941, Minneapolis, Minnesota. Association for Computational Linguistics.