@inproceedings{kruiper-etal-2021-spar,
title = "{SP}a{R}.txt, a Cheap Shallow Parsing Approach for Regulatory Texts",
author = "Kruiper, Ruben and
Konstas, Ioannis and
Gray, Alasdair J.G. and
Sadeghineko, Farhad and
Watson, Richard and
Kumar, Bimal",
editor = "Aletras, Nikolaos and
Androutsopoulos, Ion and
Barrett, Leslie and
Goanta, Catalina and
Preotiuc-Pietro, Daniel",
booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.nllp-1.14",
doi = "10.18653/v1/2021.nllp-1.14",
pages = "129--143",
abstract = "Automated Compliance Checking (ACC) systems aim to semantically parse building regulations to a set of rules. However, semantic parsing is known to be hard and requires large amounts of training data. The complexity of creating such training data has led to research that focuses on small sub-tasks, such as shallow parsing or the extraction of a limited subset of rules. This study introduces a shallow parsing task for which training data is relatively cheap to create, with the aim of learning a lexicon for ACC. We annotate a small domain-specific dataset of 200 sentences, SPaR.txt, and train a sequence tagger that achieves 79,93 F1-score on the test set. We then show through manual evaluation that the model identifies most (89,84{\%}) defined terms in a set of building regulation documents, and that both contiguous and discontiguous Multi-Word Expressions (MWE) are discovered with reasonable accuracy (70,3{\%}).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kruiper-etal-2021-spar">
<titleInfo>
<title>SPaR.txt, a Cheap Shallow Parsing Approach for Regulatory Texts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ruben</namePart>
<namePart type="family">Kruiper</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ioannis</namePart>
<namePart type="family">Konstas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alasdair</namePart>
<namePart type="given">J.G.</namePart>
<namePart type="family">Gray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Farhad</namePart>
<namePart type="family">Sadeghineko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Watson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bimal</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Natural Legal Language Processing Workshop 2021</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ion</namePart>
<namePart type="family">Androutsopoulos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leslie</namePart>
<namePart type="family">Barrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Catalina</namePart>
<namePart type="family">Goanta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preotiuc-Pietro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automated Compliance Checking (ACC) systems aim to semantically parse building regulations to a set of rules. However, semantic parsing is known to be hard and requires large amounts of training data. The complexity of creating such training data has led to research that focuses on small sub-tasks, such as shallow parsing or the extraction of a limited subset of rules. This study introduces a shallow parsing task for which training data is relatively cheap to create, with the aim of learning a lexicon for ACC. We annotate a small domain-specific dataset of 200 sentences, SPaR.txt, and train a sequence tagger that achieves 79,93 F1-score on the test set. We then show through manual evaluation that the model identifies most (89,84%) defined terms in a set of building regulation documents, and that both contiguous and discontiguous Multi-Word Expressions (MWE) are discovered with reasonable accuracy (70,3%).</abstract>
<identifier type="citekey">kruiper-etal-2021-spar</identifier>
<identifier type="doi">10.18653/v1/2021.nllp-1.14</identifier>
<location>
<url>https://aclanthology.org/2021.nllp-1.14</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>129</start>
<end>143</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SPaR.txt, a Cheap Shallow Parsing Approach for Regulatory Texts
%A Kruiper, Ruben
%A Konstas, Ioannis
%A Gray, Alasdair J.G.
%A Sadeghineko, Farhad
%A Watson, Richard
%A Kumar, Bimal
%Y Aletras, Nikolaos
%Y Androutsopoulos, Ion
%Y Barrett, Leslie
%Y Goanta, Catalina
%Y Preotiuc-Pietro, Daniel
%S Proceedings of the Natural Legal Language Processing Workshop 2021
%D 2021
%8 November
%I Association for Computational Linguistics
%C Punta Cana, Dominican Republic
%F kruiper-etal-2021-spar
%X Automated Compliance Checking (ACC) systems aim to semantically parse building regulations to a set of rules. However, semantic parsing is known to be hard and requires large amounts of training data. The complexity of creating such training data has led to research that focuses on small sub-tasks, such as shallow parsing or the extraction of a limited subset of rules. This study introduces a shallow parsing task for which training data is relatively cheap to create, with the aim of learning a lexicon for ACC. We annotate a small domain-specific dataset of 200 sentences, SPaR.txt, and train a sequence tagger that achieves 79,93 F1-score on the test set. We then show through manual evaluation that the model identifies most (89,84%) defined terms in a set of building regulation documents, and that both contiguous and discontiguous Multi-Word Expressions (MWE) are discovered with reasonable accuracy (70,3%).
%R 10.18653/v1/2021.nllp-1.14
%U https://aclanthology.org/2021.nllp-1.14
%U https://doi.org/10.18653/v1/2021.nllp-1.14
%P 129-143
Markdown (Informal)
[SPaR.txt, a Cheap Shallow Parsing Approach for Regulatory Texts](https://aclanthology.org/2021.nllp-1.14) (Kruiper et al., NLLP 2021)
ACL
- Ruben Kruiper, Ioannis Konstas, Alasdair J.G. Gray, Farhad Sadeghineko, Richard Watson, and Bimal Kumar. 2021. SPaR.txt, a Cheap Shallow Parsing Approach for Regulatory Texts. In Proceedings of the Natural Legal Language Processing Workshop 2021, pages 129–143, Punta Cana, Dominican Republic. Association for Computational Linguistics.