@inproceedings{thompson-etal-2019-overcoming,
title = "Overcoming Catastrophic Forgetting During Domain Adaptation of Neural Machine Translation",
author = "Thompson, Brian and
Gwinnup, Jeremy and
Khayrallah, Huda and
Duh, Kevin and
Koehn, Philipp",
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/N19-1209",
doi = "10.18653/v1/N19-1209",
pages = "2062--2068",
abstract = "Continued training is an effective method for domain adaptation in neural machine translation. However, in-domain gains from adaptation come at the expense of general-domain performance. In this work, we interpret the drop in general-domain performance as catastrophic forgetting of general-domain knowledge. To mitigate it, we adapt Elastic Weight Consolidation (EWC){---}a machine learning method for learning a new task without forgetting previous tasks. Our method retains the majority of general-domain performance lost in continued training without degrading in-domain performance, outperforming the previous state-of-the-art. We also explore the full range of general-domain performance available when some in-domain degradation is acceptable.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="thompson-etal-2019-overcoming">
<titleInfo>
<title>Overcoming Catastrophic Forgetting During Domain Adaptation of Neural Machine Translation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeremy</namePart>
<namePart type="family">Gwinnup</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huda</namePart>
<namePart type="family">Khayrallah</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">Philipp</namePart>
<namePart type="family">Koehn</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>Continued training is an effective method for domain adaptation in neural machine translation. However, in-domain gains from adaptation come at the expense of general-domain performance. In this work, we interpret the drop in general-domain performance as catastrophic forgetting of general-domain knowledge. To mitigate it, we adapt Elastic Weight Consolidation (EWC)—a machine learning method for learning a new task without forgetting previous tasks. Our method retains the majority of general-domain performance lost in continued training without degrading in-domain performance, outperforming the previous state-of-the-art. We also explore the full range of general-domain performance available when some in-domain degradation is acceptable.</abstract>
<identifier type="citekey">thompson-etal-2019-overcoming</identifier>
<identifier type="doi">10.18653/v1/N19-1209</identifier>
<location>
<url>https://aclanthology.org/N19-1209</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>2062</start>
<end>2068</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Overcoming Catastrophic Forgetting During Domain Adaptation of Neural Machine Translation
%A Thompson, Brian
%A Gwinnup, Jeremy
%A Khayrallah, Huda
%A Duh, Kevin
%A Koehn, Philipp
%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 thompson-etal-2019-overcoming
%X Continued training is an effective method for domain adaptation in neural machine translation. However, in-domain gains from adaptation come at the expense of general-domain performance. In this work, we interpret the drop in general-domain performance as catastrophic forgetting of general-domain knowledge. To mitigate it, we adapt Elastic Weight Consolidation (EWC)—a machine learning method for learning a new task without forgetting previous tasks. Our method retains the majority of general-domain performance lost in continued training without degrading in-domain performance, outperforming the previous state-of-the-art. We also explore the full range of general-domain performance available when some in-domain degradation is acceptable.
%R 10.18653/v1/N19-1209
%U https://aclanthology.org/N19-1209
%U https://doi.org/10.18653/v1/N19-1209
%P 2062-2068
Markdown (Informal)
[Overcoming Catastrophic Forgetting During Domain Adaptation of Neural Machine Translation](https://aclanthology.org/N19-1209) (Thompson et al., NAACL 2019)
ACL