@inproceedings{bethard-etal-2019-inferring,
title = "Inferring missing metadata from environmental policy texts",
author = "Bethard, Steven and
Laparra, Egoitz and
Wang, Sophia and
Zhao, Yiyun and
Al-Ghezi, Ragheb and
Lien, Aaron and
L{\'o}pez-Hoffman, Laura",
editor = "Alex, Beatrice and
Degaetano-Ortlieb, Stefania and
Kazantseva, Anna and
Reiter, Nils and
Szpakowicz, Stan",
booktitle = "Proceedings of the 3rd Joint {SIGHUM} Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature",
month = jun,
year = "2019",
address = "Minneapolis, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W19-2506",
doi = "10.18653/v1/W19-2506",
pages = "46--51",
abstract = "The National Environmental Policy Act (NEPA) provides a trove of data on how environmental policy decisions have been made in the United States over the last 50 years. Unfortunately, there is no central database for this information and it is too voluminous to assess manually. We describe our efforts to enable systematic research over US environmental policy by extracting and organizing metadata from the text of NEPA documents. Our contributions include collecting more than 40,000 NEPA-related documents, and evaluating rule-based baselines that establish the difficulty of three important tasks: identifying lead agencies, aligning document versions, and detecting reused text.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bethard-etal-2019-inferring">
<titleInfo>
<title>Inferring missing metadata from environmental policy texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Egoitz</namePart>
<namePart type="family">Laparra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiyun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ragheb</namePart>
<namePart type="family">Al-Ghezi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Lien</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">López-Hoffman</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 3rd Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Beatrice</namePart>
<namePart type="family">Alex</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefania</namePart>
<namePart type="family">Degaetano-Ortlieb</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Kazantseva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nils</namePart>
<namePart type="family">Reiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stan</namePart>
<namePart type="family">Szpakowicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The National Environmental Policy Act (NEPA) provides a trove of data on how environmental policy decisions have been made in the United States over the last 50 years. Unfortunately, there is no central database for this information and it is too voluminous to assess manually. We describe our efforts to enable systematic research over US environmental policy by extracting and organizing metadata from the text of NEPA documents. Our contributions include collecting more than 40,000 NEPA-related documents, and evaluating rule-based baselines that establish the difficulty of three important tasks: identifying lead agencies, aligning document versions, and detecting reused text.</abstract>
<identifier type="citekey">bethard-etal-2019-inferring</identifier>
<identifier type="doi">10.18653/v1/W19-2506</identifier>
<location>
<url>https://aclanthology.org/W19-2506</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>46</start>
<end>51</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Inferring missing metadata from environmental policy texts
%A Bethard, Steven
%A Laparra, Egoitz
%A Wang, Sophia
%A Zhao, Yiyun
%A Al-Ghezi, Ragheb
%A Lien, Aaron
%A López-Hoffman, Laura
%Y Alex, Beatrice
%Y Degaetano-Ortlieb, Stefania
%Y Kazantseva, Anna
%Y Reiter, Nils
%Y Szpakowicz, Stan
%S Proceedings of the 3rd Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, USA
%F bethard-etal-2019-inferring
%X The National Environmental Policy Act (NEPA) provides a trove of data on how environmental policy decisions have been made in the United States over the last 50 years. Unfortunately, there is no central database for this information and it is too voluminous to assess manually. We describe our efforts to enable systematic research over US environmental policy by extracting and organizing metadata from the text of NEPA documents. Our contributions include collecting more than 40,000 NEPA-related documents, and evaluating rule-based baselines that establish the difficulty of three important tasks: identifying lead agencies, aligning document versions, and detecting reused text.
%R 10.18653/v1/W19-2506
%U https://aclanthology.org/W19-2506
%U https://doi.org/10.18653/v1/W19-2506
%P 46-51
Markdown (Informal)
[Inferring missing metadata from environmental policy texts](https://aclanthology.org/W19-2506) (Bethard et al., LaTeCH 2019)
ACL
- Steven Bethard, Egoitz Laparra, Sophia Wang, Yiyun Zhao, Ragheb Al-Ghezi, Aaron Lien, and Laura López-Hoffman. 2019. Inferring missing metadata from environmental policy texts. In Proceedings of the 3rd Joint SIGHUM Workshop on Computational Linguistics for Cultural Heritage, Social Sciences, Humanities and Literature, pages 46–51, Minneapolis, USA. Association for Computational Linguistics.