@inproceedings{mishra-etal-2024-statements,
title = "Statements: Universal Information Extraction from Tables with Large Language Models for {ESG} {KPI}s",
author = "Mishra, Lokesh and
Dhibi, Sohayl and
Kim, Yusik and
Berrospi Ramis, Cesar and
Gupta, Shubham and
Dolfi, Michele and
Staar, Peter",
editor = "Stammbach, Dominik and
Ni, Jingwei and
Schimanski, Tobias and
Dutia, Kalyan and
Singh, Alok and
Bingler, Julia and
Christiaen, Christophe and
Kushwaha, Neetu and
Muccione, Veruska and
A. Vaghefi, Saeid and
Leippold, Markus",
booktitle = "Proceedings of the 1st Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2024)",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.climatenlp-1.15",
doi = "10.18653/v1/2024.climatenlp-1.15",
pages = "193--214",
abstract = "Environment, Social, and Governance (ESG) KPIs assess an organization{'}s performance on issues such as climate change, greenhouse gas emissions, water consumption, waste management, human rights, diversity, and policies. ESG reports convey this valuable quantitative information through tables. Unfortunately, extracting this information is difficult due to high variability in the table structure as well as content. We propose Statements, a novel domain agnostic data structure for extracting quantitative facts and related information. We propose translating tables to statements as a new supervised deep-learning universal information extraction task. We introduce SemTabNet - a dataset of over 100K annotated tables. Investigating a family of T5-based Statement Extraction Models, our best model generates statements which are 82{\%} similar to the ground-truth (compared to baseline of 21{\%}). We demonstrate the advantages of statements by applying our model to over 2700 tables from ESG reports. The homogeneous nature of statements permits exploratory data analysis on expansive information found in large collections of ESG reports.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mishra-etal-2024-statements">
<titleInfo>
<title>Statements: Universal Information Extraction from Tables with Large Language Models for ESG KPIs</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lokesh</namePart>
<namePart type="family">Mishra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sohayl</namePart>
<namePart type="family">Dhibi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yusik</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cesar</namePart>
<namePart type="family">Berrospi Ramis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shubham</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michele</namePart>
<namePart type="family">Dolfi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Staar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dominik</namePart>
<namePart type="family">Stammbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingwei</namePart>
<namePart type="family">Ni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tobias</namePart>
<namePart type="family">Schimanski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalyan</namePart>
<namePart type="family">Dutia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alok</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Julia</namePart>
<namePart type="family">Bingler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christophe</namePart>
<namePart type="family">Christiaen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Neetu</namePart>
<namePart type="family">Kushwaha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veruska</namePart>
<namePart type="family">Muccione</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saeid</namePart>
<namePart type="family">A. Vaghefi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Leippold</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Environment, Social, and Governance (ESG) KPIs assess an organization’s performance on issues such as climate change, greenhouse gas emissions, water consumption, waste management, human rights, diversity, and policies. ESG reports convey this valuable quantitative information through tables. Unfortunately, extracting this information is difficult due to high variability in the table structure as well as content. We propose Statements, a novel domain agnostic data structure for extracting quantitative facts and related information. We propose translating tables to statements as a new supervised deep-learning universal information extraction task. We introduce SemTabNet - a dataset of over 100K annotated tables. Investigating a family of T5-based Statement Extraction Models, our best model generates statements which are 82% similar to the ground-truth (compared to baseline of 21%). We demonstrate the advantages of statements by applying our model to over 2700 tables from ESG reports. The homogeneous nature of statements permits exploratory data analysis on expansive information found in large collections of ESG reports.</abstract>
<identifier type="citekey">mishra-etal-2024-statements</identifier>
<identifier type="doi">10.18653/v1/2024.climatenlp-1.15</identifier>
<location>
<url>https://aclanthology.org/2024.climatenlp-1.15</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>193</start>
<end>214</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Statements: Universal Information Extraction from Tables with Large Language Models for ESG KPIs
%A Mishra, Lokesh
%A Dhibi, Sohayl
%A Kim, Yusik
%A Berrospi Ramis, Cesar
%A Gupta, Shubham
%A Dolfi, Michele
%A Staar, Peter
%Y Stammbach, Dominik
%Y Ni, Jingwei
%Y Schimanski, Tobias
%Y Dutia, Kalyan
%Y Singh, Alok
%Y Bingler, Julia
%Y Christiaen, Christophe
%Y Kushwaha, Neetu
%Y Muccione, Veruska
%Y A. Vaghefi, Saeid
%Y Leippold, Markus
%S Proceedings of the 1st Workshop on Natural Language Processing Meets Climate Change (ClimateNLP 2024)
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F mishra-etal-2024-statements
%X Environment, Social, and Governance (ESG) KPIs assess an organization’s performance on issues such as climate change, greenhouse gas emissions, water consumption, waste management, human rights, diversity, and policies. ESG reports convey this valuable quantitative information through tables. Unfortunately, extracting this information is difficult due to high variability in the table structure as well as content. We propose Statements, a novel domain agnostic data structure for extracting quantitative facts and related information. We propose translating tables to statements as a new supervised deep-learning universal information extraction task. We introduce SemTabNet - a dataset of over 100K annotated tables. Investigating a family of T5-based Statement Extraction Models, our best model generates statements which are 82% similar to the ground-truth (compared to baseline of 21%). We demonstrate the advantages of statements by applying our model to over 2700 tables from ESG reports. The homogeneous nature of statements permits exploratory data analysis on expansive information found in large collections of ESG reports.
%R 10.18653/v1/2024.climatenlp-1.15
%U https://aclanthology.org/2024.climatenlp-1.15
%U https://doi.org/10.18653/v1/2024.climatenlp-1.15
%P 193-214
Markdown (Informal)
[Statements: Universal Information Extraction from Tables with Large Language Models for ESG KPIs](https://aclanthology.org/2024.climatenlp-1.15) (Mishra et al., ClimateNLP-WS 2024)
ACL