@inproceedings{akash-etal-2022-domain,
title = "Domain Representative Keywords Selection: A Probabilistic Approach",
author = "Akash, Pritom Saha and
Huang, Jie and
Chang, Kevin and
Li, Yunyao and
Popa, Lucian and
Zhai, ChengXiang",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-acl.56/",
doi = "10.18653/v1/2022.findings-acl.56",
pages = "679--692",
abstract = "We propose a probabilistic approach to select a subset of a \textit{target domain representative keywords} from a candidate set, contrasting with a context domain. Such a task is crucial for many downstream tasks in natural language processing. To contrast the target domain and the context domain, we adapt the \textit{two-component mixture model} concept to generate a distribution of candidate keywords. It provides more importance to the \textit{distinctive} keywords of the target domain than common keywords contrasting with the context domain. To support the \textit{representativeness} of the selected keywords towards the target domain, we introduce an \textit{optimization algorithm} for selecting the subset from the generated candidate distribution. We have shown that the optimization algorithm can be efficiently implemented with a near-optimal approximation guarantee. Finally, extensive experiments on multiple domains demonstrate the superiority of our approach over other baselines for the tasks of keyword summary generation and trending keywords selection."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="akash-etal-2022-domain">
<titleInfo>
<title>Domain Representative Keywords Selection: A Probabilistic Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pritom</namePart>
<namePart type="given">Saha</namePart>
<namePart type="family">Akash</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jie</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucian</namePart>
<namePart type="family">Popa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">ChengXiang</namePart>
<namePart type="family">Zhai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose a probabilistic approach to select a subset of a target domain representative keywords from a candidate set, contrasting with a context domain. Such a task is crucial for many downstream tasks in natural language processing. To contrast the target domain and the context domain, we adapt the two-component mixture model concept to generate a distribution of candidate keywords. It provides more importance to the distinctive keywords of the target domain than common keywords contrasting with the context domain. To support the representativeness of the selected keywords towards the target domain, we introduce an optimization algorithm for selecting the subset from the generated candidate distribution. We have shown that the optimization algorithm can be efficiently implemented with a near-optimal approximation guarantee. Finally, extensive experiments on multiple domains demonstrate the superiority of our approach over other baselines for the tasks of keyword summary generation and trending keywords selection.</abstract>
<identifier type="citekey">akash-etal-2022-domain</identifier>
<identifier type="doi">10.18653/v1/2022.findings-acl.56</identifier>
<location>
<url>https://aclanthology.org/2022.findings-acl.56/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>679</start>
<end>692</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Domain Representative Keywords Selection: A Probabilistic Approach
%A Akash, Pritom Saha
%A Huang, Jie
%A Chang, Kevin
%A Li, Yunyao
%A Popa, Lucian
%A Zhai, ChengXiang
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Findings of the Association for Computational Linguistics: ACL 2022
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F akash-etal-2022-domain
%X We propose a probabilistic approach to select a subset of a target domain representative keywords from a candidate set, contrasting with a context domain. Such a task is crucial for many downstream tasks in natural language processing. To contrast the target domain and the context domain, we adapt the two-component mixture model concept to generate a distribution of candidate keywords. It provides more importance to the distinctive keywords of the target domain than common keywords contrasting with the context domain. To support the representativeness of the selected keywords towards the target domain, we introduce an optimization algorithm for selecting the subset from the generated candidate distribution. We have shown that the optimization algorithm can be efficiently implemented with a near-optimal approximation guarantee. Finally, extensive experiments on multiple domains demonstrate the superiority of our approach over other baselines for the tasks of keyword summary generation and trending keywords selection.
%R 10.18653/v1/2022.findings-acl.56
%U https://aclanthology.org/2022.findings-acl.56/
%U https://doi.org/10.18653/v1/2022.findings-acl.56
%P 679-692
Markdown (Informal)
[Domain Representative Keywords Selection: A Probabilistic Approach](https://aclanthology.org/2022.findings-acl.56/) (Akash et al., Findings 2022)
ACL