@inproceedings{kobayashi-etal-2022-dataset,
title = "Dataset Construction for Scientific-Document Writing Support by Extracting Related Work Section and Citations from {PDF} Papers",
author = "Kobayashi, Keita and
Koyama, Kohei and
Narimatsu, Hiromi and
Minami, Yasuhiro",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.609",
pages = "5673--5682",
abstract = "To augment datasets used for scientific-document writing support research, we extract texts from {``}Related Work{''} sections and citation information in PDF-formatted papers published in English. The previous dataset was constructed entirely with Tex-formatted papers, from which it is easy to extract citation information. However, since many publicly available papers in various fields are provided only in PDF format, a dataset constructed using only Tex papers has limited utility. To resolve this problem, we augment the existing dataset by extracting the titles of sections using the visual features of PDF documents and extracting the Related Work section text using the explicit title information. Since text generated from the figures and footnotes appearing in the extraction target areas is considered noise, we remove instances of such text. Moreover, we map the cited paper{'}s information obtained using existing tools to citation marks detected by regular expression rules, resulting in pairs of cited paper information and text of the Related Work section. By evaluating body text extraction and citation mapping in the constructed dataset, the accuracy of the proposed dataset was found to be close to that of the previous dataset. Accordingly, we demonstrated the possibility of building a significantly augmented dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kobayashi-etal-2022-dataset">
<titleInfo>
<title>Dataset Construction for Scientific-Document Writing Support by Extracting Related Work Section and Citations from PDF Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Keita</namePart>
<namePart type="family">Kobayashi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kohei</namePart>
<namePart type="family">Koyama</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hiromi</namePart>
<namePart type="family">Narimatsu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yasuhiro</namePart>
<namePart type="family">Minami</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>To augment datasets used for scientific-document writing support research, we extract texts from “Related Work” sections and citation information in PDF-formatted papers published in English. The previous dataset was constructed entirely with Tex-formatted papers, from which it is easy to extract citation information. However, since many publicly available papers in various fields are provided only in PDF format, a dataset constructed using only Tex papers has limited utility. To resolve this problem, we augment the existing dataset by extracting the titles of sections using the visual features of PDF documents and extracting the Related Work section text using the explicit title information. Since text generated from the figures and footnotes appearing in the extraction target areas is considered noise, we remove instances of such text. Moreover, we map the cited paper’s information obtained using existing tools to citation marks detected by regular expression rules, resulting in pairs of cited paper information and text of the Related Work section. By evaluating body text extraction and citation mapping in the constructed dataset, the accuracy of the proposed dataset was found to be close to that of the previous dataset. Accordingly, we demonstrated the possibility of building a significantly augmented dataset.</abstract>
<identifier type="citekey">kobayashi-etal-2022-dataset</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.609</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>5673</start>
<end>5682</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Dataset Construction for Scientific-Document Writing Support by Extracting Related Work Section and Citations from PDF Papers
%A Kobayashi, Keita
%A Koyama, Kohei
%A Narimatsu, Hiromi
%A Minami, Yasuhiro
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F kobayashi-etal-2022-dataset
%X To augment datasets used for scientific-document writing support research, we extract texts from “Related Work” sections and citation information in PDF-formatted papers published in English. The previous dataset was constructed entirely with Tex-formatted papers, from which it is easy to extract citation information. However, since many publicly available papers in various fields are provided only in PDF format, a dataset constructed using only Tex papers has limited utility. To resolve this problem, we augment the existing dataset by extracting the titles of sections using the visual features of PDF documents and extracting the Related Work section text using the explicit title information. Since text generated from the figures and footnotes appearing in the extraction target areas is considered noise, we remove instances of such text. Moreover, we map the cited paper’s information obtained using existing tools to citation marks detected by regular expression rules, resulting in pairs of cited paper information and text of the Related Work section. By evaluating body text extraction and citation mapping in the constructed dataset, the accuracy of the proposed dataset was found to be close to that of the previous dataset. Accordingly, we demonstrated the possibility of building a significantly augmented dataset.
%U https://aclanthology.org/2022.lrec-1.609
%P 5673-5682
Markdown (Informal)
[Dataset Construction for Scientific-Document Writing Support by Extracting Related Work Section and Citations from PDF Papers](https://aclanthology.org/2022.lrec-1.609) (Kobayashi et al., LREC 2022)
ACL