@inproceedings{freitag-etal-2022-accelerating,
title = "Accelerating Human Authorship of Information Extraction Rules",
author = "Freitag, Dayne and
Cadigan, John and
Niekrasz, John and
Sasseen, Robert",
editor = "Chiticariu, Laura and
Goldberg, Yoav and
Hahn-Powell, Gus and
Morrison, Clayton T. and
Naik, Aakanksha and
Sharp, Rebecca and
Surdeanu, Mihai and
Valenzuela-Esc{\'a}rcega, Marco and
Noriega-Atala, Enrique",
booktitle = "Proceedings of the First Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Conference on Computational Linguistics",
url = "https://aclanthology.org/2022.pandl-1.6/",
pages = "45--55",
abstract = "We consider whether machine models can facilitate the human development of rule sets for information extraction. Arguing that rule-based methods possess a speed advantage in the early development of new extraction capabilities, we ask whether this advantage can be increased further through the machine facilitation of common recurring manual operations in the creation of an extraction rule set from scratch. Using a historical rule set, we reconstruct and describe the putative manual operations required to create it. In experiments targeting one key operation{---}the enumeration of words occurring in particular contexts{---}we simulate the process or corpus review and word list creation, showing that several simple interventions greatly improve recall as a function of simulated labor."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="freitag-etal-2022-accelerating">
<titleInfo>
<title>Accelerating Human Authorship of Information Extraction Rules</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">John</namePart>
<namePart type="family">Niekrasz</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>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Chiticariu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gus</namePart>
<namePart type="family">Hahn-Powell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Clayton</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Morrison</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aakanksha</namePart>
<namePart type="family">Naik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Sharp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihai</namePart>
<namePart type="family">Surdeanu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Valenzuela-Escárcega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrique</namePart>
<namePart type="family">Noriega-Atala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>International Conference on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We consider whether machine models can facilitate the human development of rule sets for information extraction. Arguing that rule-based methods possess a speed advantage in the early development of new extraction capabilities, we ask whether this advantage can be increased further through the machine facilitation of common recurring manual operations in the creation of an extraction rule set from scratch. Using a historical rule set, we reconstruct and describe the putative manual operations required to create it. In experiments targeting one key operation—the enumeration of words occurring in particular contexts—we simulate the process or corpus review and word list creation, showing that several simple interventions greatly improve recall as a function of simulated labor.</abstract>
<identifier type="citekey">freitag-etal-2022-accelerating</identifier>
<location>
<url>https://aclanthology.org/2022.pandl-1.6/</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>45</start>
<end>55</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Accelerating Human Authorship of Information Extraction Rules
%A Freitag, Dayne
%A Cadigan, John
%A Niekrasz, John
%A Sasseen, Robert
%Y Chiticariu, Laura
%Y Goldberg, Yoav
%Y Hahn-Powell, Gus
%Y Morrison, Clayton T.
%Y Naik, Aakanksha
%Y Sharp, Rebecca
%Y Surdeanu, Mihai
%Y Valenzuela-Escárcega, Marco
%Y Noriega-Atala, Enrique
%S Proceedings of the First Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning
%D 2022
%8 October
%I International Conference on Computational Linguistics
%C Gyeongju, Republic of Korea
%F freitag-etal-2022-accelerating
%X We consider whether machine models can facilitate the human development of rule sets for information extraction. Arguing that rule-based methods possess a speed advantage in the early development of new extraction capabilities, we ask whether this advantage can be increased further through the machine facilitation of common recurring manual operations in the creation of an extraction rule set from scratch. Using a historical rule set, we reconstruct and describe the putative manual operations required to create it. In experiments targeting one key operation—the enumeration of words occurring in particular contexts—we simulate the process or corpus review and word list creation, showing that several simple interventions greatly improve recall as a function of simulated labor.
%U https://aclanthology.org/2022.pandl-1.6/
%P 45-55
Markdown (Informal)
[Accelerating Human Authorship of Information Extraction Rules](https://aclanthology.org/2022.pandl-1.6/) (Freitag et al., PANDL 2022)
ACL
- Dayne Freitag, John Cadigan, John Niekrasz, and Robert Sasseen. 2022. Accelerating Human Authorship of Information Extraction Rules. In Proceedings of the First Workshop on Pattern-based Approaches to NLP in the Age of Deep Learning, pages 45–55, Gyeongju, Republic of Korea. International Conference on Computational Linguistics.