@inproceedings{kazi-etal-2021-automatically,
title = "Automatically Cataloging Scholarly Articles using Library of Congress Subject Headings",
author = "Kazi, Nazmul and
Lane, Nathaniel and
Kahanda, Indika",
editor = "Sorodoc, Ionut-Teodor and
Sushil, Madhumita and
Takmaz, Ece and
Agirre, Eneko",
booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop",
month = apr,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.eacl-srw.7",
doi = "10.18653/v1/2021.eacl-srw.7",
pages = "43--49",
abstract = "Institutes are required to catalog their articles with proper subject headings so that the users can easily retrieve relevant articles from the institutional repositories. However, due to the rate of proliferation of the number of articles in these repositories, it is becoming a challenge to manually catalog the newly added articles at the same pace. To address this challenge, we explore the feasibility of automatically annotating articles with Library of Congress Subject Headings (LCSH). We first use web scraping to extract keywords for a collection of articles from the Repository Analytics and Metrics Portal (RAMP). Then, we map these keywords to LCSH names for developing a gold-standard dataset. As a case study, using the subset of Biology-related LCSH concepts, we develop predictive models by formulating this task as a multi-label classification problem. Our experimental results demonstrate the viability of this approach for predicting LCSH for scholarly articles.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kazi-etal-2021-automatically">
<titleInfo>
<title>Automatically Cataloging Scholarly Articles using Library of Congress Subject Headings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nazmul</namePart>
<namePart type="family">Kazi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathaniel</namePart>
<namePart type="family">Lane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Indika</namePart>
<namePart type="family">Kahanda</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ionut-Teodor</namePart>
<namePart type="family">Sorodoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Madhumita</namePart>
<namePart type="family">Sushil</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ece</namePart>
<namePart type="family">Takmaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eneko</namePart>
<namePart type="family">Agirre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Institutes are required to catalog their articles with proper subject headings so that the users can easily retrieve relevant articles from the institutional repositories. However, due to the rate of proliferation of the number of articles in these repositories, it is becoming a challenge to manually catalog the newly added articles at the same pace. To address this challenge, we explore the feasibility of automatically annotating articles with Library of Congress Subject Headings (LCSH). We first use web scraping to extract keywords for a collection of articles from the Repository Analytics and Metrics Portal (RAMP). Then, we map these keywords to LCSH names for developing a gold-standard dataset. As a case study, using the subset of Biology-related LCSH concepts, we develop predictive models by formulating this task as a multi-label classification problem. Our experimental results demonstrate the viability of this approach for predicting LCSH for scholarly articles.</abstract>
<identifier type="citekey">kazi-etal-2021-automatically</identifier>
<identifier type="doi">10.18653/v1/2021.eacl-srw.7</identifier>
<location>
<url>https://aclanthology.org/2021.eacl-srw.7</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>43</start>
<end>49</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatically Cataloging Scholarly Articles using Library of Congress Subject Headings
%A Kazi, Nazmul
%A Lane, Nathaniel
%A Kahanda, Indika
%Y Sorodoc, Ionut-Teodor
%Y Sushil, Madhumita
%Y Takmaz, Ece
%Y Agirre, Eneko
%S Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Student Research Workshop
%D 2021
%8 April
%I Association for Computational Linguistics
%C Online
%F kazi-etal-2021-automatically
%X Institutes are required to catalog their articles with proper subject headings so that the users can easily retrieve relevant articles from the institutional repositories. However, due to the rate of proliferation of the number of articles in these repositories, it is becoming a challenge to manually catalog the newly added articles at the same pace. To address this challenge, we explore the feasibility of automatically annotating articles with Library of Congress Subject Headings (LCSH). We first use web scraping to extract keywords for a collection of articles from the Repository Analytics and Metrics Portal (RAMP). Then, we map these keywords to LCSH names for developing a gold-standard dataset. As a case study, using the subset of Biology-related LCSH concepts, we develop predictive models by formulating this task as a multi-label classification problem. Our experimental results demonstrate the viability of this approach for predicting LCSH for scholarly articles.
%R 10.18653/v1/2021.eacl-srw.7
%U https://aclanthology.org/2021.eacl-srw.7
%U https://doi.org/10.18653/v1/2021.eacl-srw.7
%P 43-49
Markdown (Informal)
[Automatically Cataloging Scholarly Articles using Library of Congress Subject Headings](https://aclanthology.org/2021.eacl-srw.7) (Kazi et al., EACL 2021)
ACL