@inproceedings{huang-etal-2022-lightweight,
title = "Lightweight Contextual Logical Structure Recovery",
author = "Huang, Po-Wei and
Ramesh Kashyap, Abhinav and
Qin, Yanxia and
Yang, Yajing and
Kan, Min-Yen",
editor = "Cohan, Arman and
Feigenblat, Guy and
Freitag, Dayne and
Ghosal, Tirthankar and
Herrmannova, Drahomira and
Knoth, Petr and
Lo, Kyle and
Mayr, Philipp and
Shmueli-Scheuer, Michal and
de Waard, Anita and
Wang, Lucy Lu",
booktitle = "Proceedings of the Third Workshop on Scholarly Document Processing",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.sdp-1.5/",
pages = "37--48",
abstract = "Logical structure recovery in scientific articles associates text with a semantic section of the article. Although previous work has disregarded the surrounding context of a line, we model this important information by employing line-level attention on top of a transformer-based scientific document processing pipeline. With the addition of loss function engineering and data augmentation techniques with semi-supervised learning, our method improves classification performance by 10{\%} compared to a recent state-of-the-art model. Our parsimonious, text-only method achieves a performance comparable to that of other works that use rich document features such as font and spatial position, using less data without sacrificing performance, resulting in a lightweight training pipeline."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="huang-etal-2022-lightweight">
<titleInfo>
<title>Lightweight Contextual Logical Structure Recovery</title>
</titleInfo>
<name type="personal">
<namePart type="given">Po-Wei</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Ramesh Kashyap</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yanxia</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yajing</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Third Workshop on Scholarly Document Processing</title>
</titleInfo>
<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">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">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">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">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Logical structure recovery in scientific articles associates text with a semantic section of the article. Although previous work has disregarded the surrounding context of a line, we model this important information by employing line-level attention on top of a transformer-based scientific document processing pipeline. With the addition of loss function engineering and data augmentation techniques with semi-supervised learning, our method improves classification performance by 10% compared to a recent state-of-the-art model. Our parsimonious, text-only method achieves a performance comparable to that of other works that use rich document features such as font and spatial position, using less data without sacrificing performance, resulting in a lightweight training pipeline.</abstract>
<identifier type="citekey">huang-etal-2022-lightweight</identifier>
<location>
<url>https://aclanthology.org/2022.sdp-1.5/</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>37</start>
<end>48</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Lightweight Contextual Logical Structure Recovery
%A Huang, Po-Wei
%A Ramesh Kashyap, Abhinav
%A Qin, Yanxia
%A Yang, Yajing
%A Kan, Min-Yen
%Y Cohan, Arman
%Y Feigenblat, Guy
%Y Freitag, Dayne
%Y Ghosal, Tirthankar
%Y Herrmannova, Drahomira
%Y Knoth, Petr
%Y Lo, Kyle
%Y Mayr, Philipp
%Y Shmueli-Scheuer, Michal
%Y de Waard, Anita
%Y Wang, Lucy Lu
%S Proceedings of the Third Workshop on Scholarly Document Processing
%D 2022
%8 October
%I Association for Computational Linguistics
%C Gyeongju, Republic of Korea
%F huang-etal-2022-lightweight
%X Logical structure recovery in scientific articles associates text with a semantic section of the article. Although previous work has disregarded the surrounding context of a line, we model this important information by employing line-level attention on top of a transformer-based scientific document processing pipeline. With the addition of loss function engineering and data augmentation techniques with semi-supervised learning, our method improves classification performance by 10% compared to a recent state-of-the-art model. Our parsimonious, text-only method achieves a performance comparable to that of other works that use rich document features such as font and spatial position, using less data without sacrificing performance, resulting in a lightweight training pipeline.
%U https://aclanthology.org/2022.sdp-1.5/
%P 37-48
Markdown (Informal)
[Lightweight Contextual Logical Structure Recovery](https://aclanthology.org/2022.sdp-1.5/) (Huang et al., sdp 2022)
ACL
- Po-Wei Huang, Abhinav Ramesh Kashyap, Yanxia Qin, Yajing Yang, and Min-Yen Kan. 2022. Lightweight Contextual Logical Structure Recovery. In Proceedings of the Third Workshop on Scholarly Document Processing, pages 37–48, Gyeongju, Republic of Korea. Association for Computational Linguistics.