@inproceedings{ling-chen-2020-deeppapercomposer,
title = "{D}eep{P}aper{C}omposer: A Simple Solution for Training Data Preparation for Parsing Research Papers",
author = "Ling, Meng and
Chen, Jian",
editor = "Chandrasekaran, Muthu Kumar and
de Waard, Anita and
Feigenblat, Guy and
Freitag, Dayne and
Ghosal, Tirthankar and
Hovy, Eduard and
Knoth, Petr and
Konopnicki, David and
Mayr, Philipp and
Patton, Robert M. and
Shmueli-Scheuer, Michal",
booktitle = "Proceedings of the First Workshop on Scholarly Document Processing",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.sdp-1.10/",
doi = "10.18653/v1/2020.sdp-1.10",
pages = "91--96",
abstract = "We present DeepPaperComposer, a simple solution for preparing highly accurate (100{\%}) training data without manual labeling to extract content from scholarly articles using convolutional neural networks (CNNs). We used our approach to generate data and trained CNNs to extract eight categories of both textual (titles, abstracts, headers, figure and table captions, and other texts) and non-textural content (figures and tables) from 30 years of IEEE VIS conference papers, of which a third were scanned bitmap PDFs. We curated this dataset and named it VISpaper-3K. We then showed our initial benchmark performance using VISpaper-3K over itself and CS-150 using YOLOv3 and Faster-RCNN. We open-source DeepPaperComposer of our training data generation and released the resulting annotation data VISpaper-3K to promote re-producible research."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ling-chen-2020-deeppapercomposer">
<titleInfo>
<title>DeepPaperComposer: A Simple Solution for Training Data Preparation for Parsing Research Papers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Ling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Scholarly Document Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Muthu</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Chandrasekaran</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">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">Eduard</namePart>
<namePart type="family">Hovy</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">David</namePart>
<namePart type="family">Konopnicki</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present DeepPaperComposer, a simple solution for preparing highly accurate (100%) training data without manual labeling to extract content from scholarly articles using convolutional neural networks (CNNs). We used our approach to generate data and trained CNNs to extract eight categories of both textual (titles, abstracts, headers, figure and table captions, and other texts) and non-textural content (figures and tables) from 30 years of IEEE VIS conference papers, of which a third were scanned bitmap PDFs. We curated this dataset and named it VISpaper-3K. We then showed our initial benchmark performance using VISpaper-3K over itself and CS-150 using YOLOv3 and Faster-RCNN. We open-source DeepPaperComposer of our training data generation and released the resulting annotation data VISpaper-3K to promote re-producible research.</abstract>
<identifier type="citekey">ling-chen-2020-deeppapercomposer</identifier>
<identifier type="doi">10.18653/v1/2020.sdp-1.10</identifier>
<location>
<url>https://aclanthology.org/2020.sdp-1.10/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>91</start>
<end>96</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DeepPaperComposer: A Simple Solution for Training Data Preparation for Parsing Research Papers
%A Ling, Meng
%A Chen, Jian
%Y Chandrasekaran, Muthu Kumar
%Y de Waard, Anita
%Y Feigenblat, Guy
%Y Freitag, Dayne
%Y Ghosal, Tirthankar
%Y Hovy, Eduard
%Y Knoth, Petr
%Y Konopnicki, David
%Y Mayr, Philipp
%Y Patton, Robert M.
%Y Shmueli-Scheuer, Michal
%S Proceedings of the First Workshop on Scholarly Document Processing
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F ling-chen-2020-deeppapercomposer
%X We present DeepPaperComposer, a simple solution for preparing highly accurate (100%) training data without manual labeling to extract content from scholarly articles using convolutional neural networks (CNNs). We used our approach to generate data and trained CNNs to extract eight categories of both textual (titles, abstracts, headers, figure and table captions, and other texts) and non-textural content (figures and tables) from 30 years of IEEE VIS conference papers, of which a third were scanned bitmap PDFs. We curated this dataset and named it VISpaper-3K. We then showed our initial benchmark performance using VISpaper-3K over itself and CS-150 using YOLOv3 and Faster-RCNN. We open-source DeepPaperComposer of our training data generation and released the resulting annotation data VISpaper-3K to promote re-producible research.
%R 10.18653/v1/2020.sdp-1.10
%U https://aclanthology.org/2020.sdp-1.10/
%U https://doi.org/10.18653/v1/2020.sdp-1.10
%P 91-96
Markdown (Informal)
[DeepPaperComposer: A Simple Solution for Training Data Preparation for Parsing Research Papers](https://aclanthology.org/2020.sdp-1.10/) (Ling & Chen, sdp 2020)
ACL