@inproceedings{gupta-etal-2023-discomat,
title = "{D}i{SC}o{M}a{T}: Distantly Supervised Composition Extraction from Tables in Materials Science Articles",
author = "Gupta, Tanishq and
Zaki, Mohd and
Khatsuriya, Devanshi and
Hira, Kausik and
Krishnan, N M Anoop and
{Mausam}",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-long.753",
doi = "10.18653/v1/2023.acl-long.753",
pages = "13465--13483",
abstract = "A crucial component in the curation of KB for a scientific domain (e.g., materials science, food {\&} nutrition, fuels) is information extraction from tables in the domain{'}s published research articles. To facilitate research in this direction, we define a novel NLP task of extracting compositions of materials (e.g., glasses) from tables in materials science papers. The task involves solving several challenges in concert, such as tables that mention compositions have highly varying structures; text in captions and full paper needs to be incorporated along with data in tables; and regular languages for numbers, chemical compounds, and composition expressions must be integrated into the model. We release a training dataset comprising 4,408 distantly supervised tables, along with 1,475 manually annotated dev and test tables. We also present DiSCoMaT, a strong baseline that combines multiple graph neural networks with several task-specific regular expressions, features, and constraints. We show that DiSCoMaT outperforms recent table processing architectures by significant margins. We release our code and data for further research on this challenging IE task from scientific tables.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-etal-2023-discomat">
<titleInfo>
<title>DiSCoMaT: Distantly Supervised Composition Extraction from Tables in Materials Science Articles</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tanishq</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohd</namePart>
<namePart type="family">Zaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Devanshi</namePart>
<namePart type="family">Khatsuriya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kausik</namePart>
<namePart type="family">Hira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">N</namePart>
<namePart type="given">M</namePart>
<namePart type="given">Anoop</namePart>
<namePart type="family">Krishnan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name>
<namePart>Mausam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rogers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jordan</namePart>
<namePart type="family">Boyd-Graber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naoaki</namePart>
<namePart type="family">Okazaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A crucial component in the curation of KB for a scientific domain (e.g., materials science, food & nutrition, fuels) is information extraction from tables in the domain’s published research articles. To facilitate research in this direction, we define a novel NLP task of extracting compositions of materials (e.g., glasses) from tables in materials science papers. The task involves solving several challenges in concert, such as tables that mention compositions have highly varying structures; text in captions and full paper needs to be incorporated along with data in tables; and regular languages for numbers, chemical compounds, and composition expressions must be integrated into the model. We release a training dataset comprising 4,408 distantly supervised tables, along with 1,475 manually annotated dev and test tables. We also present DiSCoMaT, a strong baseline that combines multiple graph neural networks with several task-specific regular expressions, features, and constraints. We show that DiSCoMaT outperforms recent table processing architectures by significant margins. We release our code and data for further research on this challenging IE task from scientific tables.</abstract>
<identifier type="citekey">gupta-etal-2023-discomat</identifier>
<identifier type="doi">10.18653/v1/2023.acl-long.753</identifier>
<location>
<url>https://aclanthology.org/2023.acl-long.753</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>13465</start>
<end>13483</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DiSCoMaT: Distantly Supervised Composition Extraction from Tables in Materials Science Articles
%A Gupta, Tanishq
%A Zaki, Mohd
%A Khatsuriya, Devanshi
%A Hira, Kausik
%A Krishnan, N. M. Anoop
%Y Rogers, Anna
%Y Boyd-Graber, Jordan
%Y Okazaki, Naoaki
%A Mausam
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F gupta-etal-2023-discomat
%X A crucial component in the curation of KB for a scientific domain (e.g., materials science, food & nutrition, fuels) is information extraction from tables in the domain’s published research articles. To facilitate research in this direction, we define a novel NLP task of extracting compositions of materials (e.g., glasses) from tables in materials science papers. The task involves solving several challenges in concert, such as tables that mention compositions have highly varying structures; text in captions and full paper needs to be incorporated along with data in tables; and regular languages for numbers, chemical compounds, and composition expressions must be integrated into the model. We release a training dataset comprising 4,408 distantly supervised tables, along with 1,475 manually annotated dev and test tables. We also present DiSCoMaT, a strong baseline that combines multiple graph neural networks with several task-specific regular expressions, features, and constraints. We show that DiSCoMaT outperforms recent table processing architectures by significant margins. We release our code and data for further research on this challenging IE task from scientific tables.
%R 10.18653/v1/2023.acl-long.753
%U https://aclanthology.org/2023.acl-long.753
%U https://doi.org/10.18653/v1/2023.acl-long.753
%P 13465-13483
Markdown (Informal)
[DiSCoMaT: Distantly Supervised Composition Extraction from Tables in Materials Science Articles](https://aclanthology.org/2023.acl-long.753) (Gupta et al., ACL 2023)
ACL