@inproceedings{agrawal-etal-2019-scalable,
title = "Scalable, Semi-Supervised Extraction of Structured Information from Scientific Literature",
author = "Agrawal, Kritika and
Mittal, Aakash and
Pudi, Vikram",
editor = "Nastase, Vivi and
Roth, Benjamin and
Dietz, Laura and
McCallum, Andrew",
booktitle = "Proceedings of the Workshop on Extracting Structured Knowledge from Scientific Publications",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-2602",
doi = "10.18653/v1/W19-2602",
pages = "11--20",
abstract = "As scientific communities grow and evolve, there is a high demand for improved methods for finding relevant papers, comparing papers on similar topics and studying trends in the research community. All these tasks involve the common problem of extracting structured information from scientific articles. In this paper, we propose a novel, scalable, semi-supervised method for extracting relevant structured information from the vast available raw scientific literature. We extract the fundamental concepts of {``}aim{''}, {''}method{''} and {``}result{''} from scientific articles and use them to construct a knowledge graph. Our algorithm makes use of domain-based word embedding and the bootstrap framework. Our experiments show that our system achieves precision and recall comparable to the state of the art. We also show the domain independence of our algorithm by analyzing the research trends of two distinct communities - computational linguistics and computer vision.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="agrawal-etal-2019-scalable">
<titleInfo>
<title>Scalable, Semi-Supervised Extraction of Structured Information from Scientific Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kritika</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aakash</namePart>
<namePart type="family">Mittal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vikram</namePart>
<namePart type="family">Pudi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Workshop on Extracting Structured Knowledge from Scientific Publications</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vivi</namePart>
<namePart type="family">Nastase</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Benjamin</namePart>
<namePart type="family">Roth</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Dietz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrew</namePart>
<namePart type="family">McCallum</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As scientific communities grow and evolve, there is a high demand for improved methods for finding relevant papers, comparing papers on similar topics and studying trends in the research community. All these tasks involve the common problem of extracting structured information from scientific articles. In this paper, we propose a novel, scalable, semi-supervised method for extracting relevant structured information from the vast available raw scientific literature. We extract the fundamental concepts of “aim”, ”method” and “result” from scientific articles and use them to construct a knowledge graph. Our algorithm makes use of domain-based word embedding and the bootstrap framework. Our experiments show that our system achieves precision and recall comparable to the state of the art. We also show the domain independence of our algorithm by analyzing the research trends of two distinct communities - computational linguistics and computer vision.</abstract>
<identifier type="citekey">agrawal-etal-2019-scalable</identifier>
<identifier type="doi">10.18653/v1/W19-2602</identifier>
<location>
<url>https://aclanthology.org/W19-2602</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>11</start>
<end>20</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Scalable, Semi-Supervised Extraction of Structured Information from Scientific Literature
%A Agrawal, Kritika
%A Mittal, Aakash
%A Pudi, Vikram
%Y Nastase, Vivi
%Y Roth, Benjamin
%Y Dietz, Laura
%Y McCallum, Andrew
%S Proceedings of the Workshop on Extracting Structured Knowledge from Scientific Publications
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F agrawal-etal-2019-scalable
%X As scientific communities grow and evolve, there is a high demand for improved methods for finding relevant papers, comparing papers on similar topics and studying trends in the research community. All these tasks involve the common problem of extracting structured information from scientific articles. In this paper, we propose a novel, scalable, semi-supervised method for extracting relevant structured information from the vast available raw scientific literature. We extract the fundamental concepts of “aim”, ”method” and “result” from scientific articles and use them to construct a knowledge graph. Our algorithm makes use of domain-based word embedding and the bootstrap framework. Our experiments show that our system achieves precision and recall comparable to the state of the art. We also show the domain independence of our algorithm by analyzing the research trends of two distinct communities - computational linguistics and computer vision.
%R 10.18653/v1/W19-2602
%U https://aclanthology.org/W19-2602
%U https://doi.org/10.18653/v1/W19-2602
%P 11-20
Markdown (Informal)
[Scalable, Semi-Supervised Extraction of Structured Information from Scientific Literature](https://aclanthology.org/W19-2602) (Agrawal et al., NAACL 2019)
ACL