@inproceedings{freitag-etal-2022-valet,
title = "Valet: Rule-Based Information Extraction for Rapid Deployment",
author = "Freitag, Dayne and
Cadigan, John and
Sasseen, Robert and
Kalmar, Paul",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.55",
pages = "524--533",
abstract = "We present VALET, a framework for rule-based information extraction written in Python. VALET departs from legacy approaches predicated on cascading finite-state transducers, instead offering direct support for mixing heterogeneous information{--}lexical, orthographic, syntactic, corpus-analytic{--}in a succinct syntax that supports context-free idioms. We show how a handful of rules suffices to implement sophisticated matching, and describe a user interface that facilitates exploration for development and maintenance of rule sets. Arguing that rule-based information extraction is an important methodology early in the development cycle, we describe an experiment in which a VALET model is used to annotate examples for a machine learning extraction model. While learning to emulate the extraction rules, the resulting model generalizes them, recognizing valid extraction targets the rules failed to detect.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="freitag-etal-2022-valet">
<titleInfo>
<title>Valet: Rule-Based Information Extraction for Rapid Deployment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dayne</namePart>
<namePart type="family">Freitag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="family">Cadigan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Sasseen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Kalmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We present VALET, a framework for rule-based information extraction written in Python. VALET departs from legacy approaches predicated on cascading finite-state transducers, instead offering direct support for mixing heterogeneous information–lexical, orthographic, syntactic, corpus-analytic–in a succinct syntax that supports context-free idioms. We show how a handful of rules suffices to implement sophisticated matching, and describe a user interface that facilitates exploration for development and maintenance of rule sets. Arguing that rule-based information extraction is an important methodology early in the development cycle, we describe an experiment in which a VALET model is used to annotate examples for a machine learning extraction model. While learning to emulate the extraction rules, the resulting model generalizes them, recognizing valid extraction targets the rules failed to detect.</abstract>
<identifier type="citekey">freitag-etal-2022-valet</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.55</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>524</start>
<end>533</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Valet: Rule-Based Information Extraction for Rapid Deployment
%A Freitag, Dayne
%A Cadigan, John
%A Sasseen, Robert
%A Kalmar, Paul
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F freitag-etal-2022-valet
%X We present VALET, a framework for rule-based information extraction written in Python. VALET departs from legacy approaches predicated on cascading finite-state transducers, instead offering direct support for mixing heterogeneous information–lexical, orthographic, syntactic, corpus-analytic–in a succinct syntax that supports context-free idioms. We show how a handful of rules suffices to implement sophisticated matching, and describe a user interface that facilitates exploration for development and maintenance of rule sets. Arguing that rule-based information extraction is an important methodology early in the development cycle, we describe an experiment in which a VALET model is used to annotate examples for a machine learning extraction model. While learning to emulate the extraction rules, the resulting model generalizes them, recognizing valid extraction targets the rules failed to detect.
%U https://aclanthology.org/2022.lrec-1.55
%P 524-533
Markdown (Informal)
[Valet: Rule-Based Information Extraction for Rapid Deployment](https://aclanthology.org/2022.lrec-1.55) (Freitag et al., LREC 2022)
ACL