@inproceedings{kim-etal-2017-adversarial,
title = "Adversarial Adaptation of Synthetic or Stale Data",
author = "Kim, Young-Bum and
Stratos, Karl and
Kim, Dongchan",
editor = "Barzilay, Regina and
Kan, Min-Yen",
booktitle = "Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2017",
address = "Vancouver, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/P17-1119/",
doi = "10.18653/v1/P17-1119",
pages = "1297--1307",
abstract = "Two types of data shift common in practice are 1. transferring from synthetic data to live user data (a deployment shift), and 2. transferring from stale data to current data (a temporal shift). Both cause a distribution mismatch between training and evaluation, leading to a model that overfits the flawed training data and performs poorly on the test data. We propose a solution to this mismatch problem by framing it as domain adaptation, treating the flawed training dataset as a source domain and the evaluation dataset as a target domain. To this end, we use and build on several recent advances in neural domain adaptation such as adversarial training (Ganinet al., 2016) and domain separation network (Bousmalis et al., 2016), proposing a new effective adversarial training scheme. In both supervised and unsupervised adaptation scenarios, our approach yields clear improvement over strong baselines."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2017-adversarial">
<titleInfo>
<title>Adversarial Adaptation of Synthetic or Stale Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Young-Bum</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karl</namePart>
<namePart type="family">Stratos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dongchan</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Regina</namePart>
<namePart type="family">Barzilay</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vancouver, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Two types of data shift common in practice are 1. transferring from synthetic data to live user data (a deployment shift), and 2. transferring from stale data to current data (a temporal shift). Both cause a distribution mismatch between training and evaluation, leading to a model that overfits the flawed training data and performs poorly on the test data. We propose a solution to this mismatch problem by framing it as domain adaptation, treating the flawed training dataset as a source domain and the evaluation dataset as a target domain. To this end, we use and build on several recent advances in neural domain adaptation such as adversarial training (Ganinet al., 2016) and domain separation network (Bousmalis et al., 2016), proposing a new effective adversarial training scheme. In both supervised and unsupervised adaptation scenarios, our approach yields clear improvement over strong baselines.</abstract>
<identifier type="citekey">kim-etal-2017-adversarial</identifier>
<identifier type="doi">10.18653/v1/P17-1119</identifier>
<location>
<url>https://aclanthology.org/P17-1119/</url>
</location>
<part>
<date>2017-07</date>
<extent unit="page">
<start>1297</start>
<end>1307</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Adversarial Adaptation of Synthetic or Stale Data
%A Kim, Young-Bum
%A Stratos, Karl
%A Kim, Dongchan
%Y Barzilay, Regina
%Y Kan, Min-Yen
%S Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2017
%8 July
%I Association for Computational Linguistics
%C Vancouver, Canada
%F kim-etal-2017-adversarial
%X Two types of data shift common in practice are 1. transferring from synthetic data to live user data (a deployment shift), and 2. transferring from stale data to current data (a temporal shift). Both cause a distribution mismatch between training and evaluation, leading to a model that overfits the flawed training data and performs poorly on the test data. We propose a solution to this mismatch problem by framing it as domain adaptation, treating the flawed training dataset as a source domain and the evaluation dataset as a target domain. To this end, we use and build on several recent advances in neural domain adaptation such as adversarial training (Ganinet al., 2016) and domain separation network (Bousmalis et al., 2016), proposing a new effective adversarial training scheme. In both supervised and unsupervised adaptation scenarios, our approach yields clear improvement over strong baselines.
%R 10.18653/v1/P17-1119
%U https://aclanthology.org/P17-1119/
%U https://doi.org/10.18653/v1/P17-1119
%P 1297-1307
Markdown (Informal)
[Adversarial Adaptation of Synthetic or Stale Data](https://aclanthology.org/P17-1119/) (Kim et al., ACL 2017)
ACL
- Young-Bum Kim, Karl Stratos, and Dongchan Kim. 2017. Adversarial Adaptation of Synthetic or Stale Data. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1297–1307, Vancouver, Canada. Association for Computational Linguistics.