@inproceedings{kontoulis-etal-2021-keyphrase,
title = "Keyphrase Extraction from Scientific Articles via Extractive Summarization",
author = "Kontoulis, Chrysovalantis Giorgos and
Papagiannopoulou, Eirini and
Tsoumakas, Grigorios",
editor = "Beltagy, Iz and
Cohan, Arman and
Feigenblat, Guy and
Freitag, Dayne and
Ghosal, Tirthankar and
Hall, Keith and
Herrmannova, Drahomira and
Knoth, Petr and
Lo, Kyle and
Mayr, Philipp and
Patton, Robert M. and
Shmueli-Scheuer, Michal and
de Waard, Anita and
Wang, Kuansan and
Wang, Lucy Lu",
booktitle = "Proceedings of the Second Workshop on Scholarly Document Processing",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.sdp-1.6",
doi = "10.18653/v1/2021.sdp-1.6",
pages = "49--55",
abstract = "Automatically extracting keyphrases from scholarly documents leads to a valuable concise representation that humans can understand and machines can process for tasks, such as information retrieval, article clustering and article classification. This paper is concerned with the parts of a scientific article that should be given as input to keyphrase extraction methods. Recent deep learning methods take titles and abstracts as input due to the increased computational complexity in processing long sequences, whereas traditional approaches can also work with full-texts. Titles and abstracts are dense in keyphrases, but often miss important aspects of the articles, while full-texts on the other hand are richer in keyphrases but much noisier. To address this trade-off, we propose the use of extractive summarization models on the full-texts of scholarly documents. Our empirical study on 3 article collections using 3 keyphrase extraction methods shows promising results.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kontoulis-etal-2021-keyphrase">
<titleInfo>
<title>Keyphrase Extraction from Scientific Articles via Extractive Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chrysovalantis</namePart>
<namePart type="given">Giorgos</namePart>
<namePart type="family">Kontoulis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eirini</namePart>
<namePart type="family">Papagiannopoulou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grigorios</namePart>
<namePart type="family">Tsoumakas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Scholarly Document Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arman</namePart>
<namePart type="family">Cohan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Feigenblat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dayne</namePart>
<namePart type="family">Freitag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tirthankar</namePart>
<namePart type="family">Ghosal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Keith</namePart>
<namePart type="family">Hall</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Drahomira</namePart>
<namePart type="family">Herrmannova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Petr</namePart>
<namePart type="family">Knoth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kyle</namePart>
<namePart type="family">Lo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Mayr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Patton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michal</namePart>
<namePart type="family">Shmueli-Scheuer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anita</namePart>
<namePart type="family">de Waard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kuansan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucy</namePart>
<namePart type="given">Lu</namePart>
<namePart type="family">Wang</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>Automatically extracting keyphrases from scholarly documents leads to a valuable concise representation that humans can understand and machines can process for tasks, such as information retrieval, article clustering and article classification. This paper is concerned with the parts of a scientific article that should be given as input to keyphrase extraction methods. Recent deep learning methods take titles and abstracts as input due to the increased computational complexity in processing long sequences, whereas traditional approaches can also work with full-texts. Titles and abstracts are dense in keyphrases, but often miss important aspects of the articles, while full-texts on the other hand are richer in keyphrases but much noisier. To address this trade-off, we propose the use of extractive summarization models on the full-texts of scholarly documents. Our empirical study on 3 article collections using 3 keyphrase extraction methods shows promising results.</abstract>
<identifier type="citekey">kontoulis-etal-2021-keyphrase</identifier>
<identifier type="doi">10.18653/v1/2021.sdp-1.6</identifier>
<location>
<url>https://aclanthology.org/2021.sdp-1.6</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>49</start>
<end>55</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Keyphrase Extraction from Scientific Articles via Extractive Summarization
%A Kontoulis, Chrysovalantis Giorgos
%A Papagiannopoulou, Eirini
%A Tsoumakas, Grigorios
%Y Beltagy, Iz
%Y Cohan, Arman
%Y Feigenblat, Guy
%Y Freitag, Dayne
%Y Ghosal, Tirthankar
%Y Hall, Keith
%Y Herrmannova, Drahomira
%Y Knoth, Petr
%Y Lo, Kyle
%Y Mayr, Philipp
%Y Patton, Robert M.
%Y Shmueli-Scheuer, Michal
%Y de Waard, Anita
%Y Wang, Kuansan
%Y Wang, Lucy Lu
%S Proceedings of the Second Workshop on Scholarly Document Processing
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F kontoulis-etal-2021-keyphrase
%X Automatically extracting keyphrases from scholarly documents leads to a valuable concise representation that humans can understand and machines can process for tasks, such as information retrieval, article clustering and article classification. This paper is concerned with the parts of a scientific article that should be given as input to keyphrase extraction methods. Recent deep learning methods take titles and abstracts as input due to the increased computational complexity in processing long sequences, whereas traditional approaches can also work with full-texts. Titles and abstracts are dense in keyphrases, but often miss important aspects of the articles, while full-texts on the other hand are richer in keyphrases but much noisier. To address this trade-off, we propose the use of extractive summarization models on the full-texts of scholarly documents. Our empirical study on 3 article collections using 3 keyphrase extraction methods shows promising results.
%R 10.18653/v1/2021.sdp-1.6
%U https://aclanthology.org/2021.sdp-1.6
%U https://doi.org/10.18653/v1/2021.sdp-1.6
%P 49-55
Markdown (Informal)
[Keyphrase Extraction from Scientific Articles via Extractive Summarization](https://aclanthology.org/2021.sdp-1.6) (Kontoulis et al., sdp 2021)
ACL