@inproceedings{kamath-etal-2019-reversing,
title = "Reversing Gradients in Adversarial Domain Adaptation for Question Deduplication and Textual Entailment Tasks",
author = "Kamath, Anush and
Gupta, Sparsh and
Carvalho, Vitor",
editor = "Korhonen, Anna and
Traum, David and
M{\`a}rquez, Llu{\'\i}s",
booktitle = "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2019",
address = "Florence, Italy",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P19-1556",
doi = "10.18653/v1/P19-1556",
pages = "5545--5550",
abstract = "Adversarial domain adaptation has been recently proposed as an effective technique for textual matching tasks, such as question deduplication. Here we investigate the use of gradient reversal on adversarial domain adaptation to explicitly learn both shared and unshared (domain specific) representations between two textual domains. In doing so, gradient reversal learns features that explicitly compensate for domain mismatch, while still distilling domain specific knowledge that can improve target domain accuracy. We evaluate reversing gradients for adversarial adaptation on multiple domains, and demonstrate that it significantly outperforms other methods on question deduplication as well as on recognizing textual entailment (RTE) tasks, achieving up to 7{\%} absolute boost in base model accuracy on some datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kamath-etal-2019-reversing">
<titleInfo>
<title>Reversing Gradients in Adversarial Domain Adaptation for Question Deduplication and Textual Entailment Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anush</namePart>
<namePart type="family">Kamath</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sparsh</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vitor</namePart>
<namePart type="family">Carvalho</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Traum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lluís</namePart>
<namePart type="family">Màrquez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Florence, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Adversarial domain adaptation has been recently proposed as an effective technique for textual matching tasks, such as question deduplication. Here we investigate the use of gradient reversal on adversarial domain adaptation to explicitly learn both shared and unshared (domain specific) representations between two textual domains. In doing so, gradient reversal learns features that explicitly compensate for domain mismatch, while still distilling domain specific knowledge that can improve target domain accuracy. We evaluate reversing gradients for adversarial adaptation on multiple domains, and demonstrate that it significantly outperforms other methods on question deduplication as well as on recognizing textual entailment (RTE) tasks, achieving up to 7% absolute boost in base model accuracy on some datasets.</abstract>
<identifier type="citekey">kamath-etal-2019-reversing</identifier>
<identifier type="doi">10.18653/v1/P19-1556</identifier>
<location>
<url>https://aclanthology.org/P19-1556</url>
</location>
<part>
<date>2019-07</date>
<extent unit="page">
<start>5545</start>
<end>5550</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reversing Gradients in Adversarial Domain Adaptation for Question Deduplication and Textual Entailment Tasks
%A Kamath, Anush
%A Gupta, Sparsh
%A Carvalho, Vitor
%Y Korhonen, Anna
%Y Traum, David
%Y Màrquez, Lluís
%S Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
%D 2019
%8 July
%I Association for Computational Linguistics
%C Florence, Italy
%F kamath-etal-2019-reversing
%X Adversarial domain adaptation has been recently proposed as an effective technique for textual matching tasks, such as question deduplication. Here we investigate the use of gradient reversal on adversarial domain adaptation to explicitly learn both shared and unshared (domain specific) representations between two textual domains. In doing so, gradient reversal learns features that explicitly compensate for domain mismatch, while still distilling domain specific knowledge that can improve target domain accuracy. We evaluate reversing gradients for adversarial adaptation on multiple domains, and demonstrate that it significantly outperforms other methods on question deduplication as well as on recognizing textual entailment (RTE) tasks, achieving up to 7% absolute boost in base model accuracy on some datasets.
%R 10.18653/v1/P19-1556
%U https://aclanthology.org/P19-1556
%U https://doi.org/10.18653/v1/P19-1556
%P 5545-5550
Markdown (Informal)
[Reversing Gradients in Adversarial Domain Adaptation for Question Deduplication and Textual Entailment Tasks](https://aclanthology.org/P19-1556) (Kamath et al., ACL 2019)
ACL