@inproceedings{peng-zhang-2020-weighed,
title = "Weighed Domain-Invariant Representation Learning for Cross-domain Sentiment Analysis",
author = "Peng, Minlong and
Zhang, Qi",
booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
month = dec,
year = "2020",
address = "Barcelona, Spain (Online)",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2020.coling-main.22",
doi = "10.18653/v1/2020.coling-main.22",
pages = "251--265",
abstract = "Cross-domain sentiment analysis is currently a hot topic in both the research and industrial areas. One of the most popular framework for the task is domain-invariant representation learning (DIRL), which aims to learn a distribution-invariant feature representation across domains. However, in this work, we find out that applying DIRL may degrade domain adaptation performance when the label distribution $\textrm{P}(\textrm{Y})$ changes across domains. To address this problem, we propose a modification to DIRL, obtaining a novel weighted domain-invariant representation learning (WDIRL) framework. We show that it is easy to transfer existing models of the DIRL framework to the WDIRL framework. Empirical studies on extensive cross-domain sentiment analysis tasks verified our statements and showed the effectiveness of our proposed solution.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="peng-zhang-2020-weighed">
<titleInfo>
<title>Weighed Domain-Invariant Representation Learning for Cross-domain Sentiment Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minlong</namePart>
<namePart type="family">Peng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-dec</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 28th International Conference on Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Barcelona, Spain (Online)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Cross-domain sentiment analysis is currently a hot topic in both the research and industrial areas. One of the most popular framework for the task is domain-invariant representation learning (DIRL), which aims to learn a distribution-invariant feature representation across domains. However, in this work, we find out that applying DIRL may degrade domain adaptation performance when the label distribution $\textrmP(\textrmY)$ changes across domains. To address this problem, we propose a modification to DIRL, obtaining a novel weighted domain-invariant representation learning (WDIRL) framework. We show that it is easy to transfer existing models of the DIRL framework to the WDIRL framework. Empirical studies on extensive cross-domain sentiment analysis tasks verified our statements and showed the effectiveness of our proposed solution.</abstract>
<identifier type="citekey">peng-zhang-2020-weighed</identifier>
<identifier type="doi">10.18653/v1/2020.coling-main.22</identifier>
<location>
<url>https://aclanthology.org/2020.coling-main.22</url>
</location>
<part>
<date>2020-dec</date>
<extent unit="page">
<start>251</start>
<end>265</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Weighed Domain-Invariant Representation Learning for Cross-domain Sentiment Analysis
%A Peng, Minlong
%A Zhang, Qi
%S Proceedings of the 28th International Conference on Computational Linguistics
%D 2020
%8 dec
%I International Committee on Computational Linguistics
%C Barcelona, Spain (Online)
%F peng-zhang-2020-weighed
%X Cross-domain sentiment analysis is currently a hot topic in both the research and industrial areas. One of the most popular framework for the task is domain-invariant representation learning (DIRL), which aims to learn a distribution-invariant feature representation across domains. However, in this work, we find out that applying DIRL may degrade domain adaptation performance when the label distribution $\textrmP(\textrmY)$ changes across domains. To address this problem, we propose a modification to DIRL, obtaining a novel weighted domain-invariant representation learning (WDIRL) framework. We show that it is easy to transfer existing models of the DIRL framework to the WDIRL framework. Empirical studies on extensive cross-domain sentiment analysis tasks verified our statements and showed the effectiveness of our proposed solution.
%R 10.18653/v1/2020.coling-main.22
%U https://aclanthology.org/2020.coling-main.22
%U https://doi.org/10.18653/v1/2020.coling-main.22
%P 251-265
Markdown (Informal)
[Weighed Domain-Invariant Representation Learning for Cross-domain Sentiment Analysis](https://aclanthology.org/2020.coling-main.22) (Peng & Zhang, COLING 2020)
ACL