@inproceedings{vacareanu-etal-2022-human,
title = "A Human-machine Interface for Few-shot Rule Synthesis for Information Extraction",
author = "Vacareanu, Robert and
Barbosa, George C.G. and
Noriega-Atala, Enrique and
Hahn-Powell, Gus and
Sharp, Rebecca and
Valenzuela-Esc{\'a}rcega, Marco A. and
Surdeanu, Mihai",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: System Demonstrations",
month = jul,
year = "2022",
address = "Hybrid: Seattle, Washington + Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-demo.8",
doi = "10.18653/v1/2022.naacl-demo.8",
pages = "64--70",
abstract = "We propose a system that assists a user in constructing transparent information extraction models, consisting of patterns (or rules) written in a declarative language, through program synthesis.Users of our system can specify their requirements through the use of examples,which are collected with a search interface.The rule-synthesis system proposes rule candidates and the results of applying them on a textual corpus; the user has the option to accept the candidate, request another option, or adjust the examples provided to the system.Through an interactive evaluation, we show that our approach generates high-precision rules even in a 1-shot setting. On a second evaluation on a widely-used relation extraction dataset (TACRED), our method generates rules that outperform considerably manually written patterns.Our code, demo, and documentation is available at https://clulab.github.io/odinsynth.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vacareanu-etal-2022-human">
<titleInfo>
<title>A Human-machine Interface for Few-shot Rule Synthesis for Information Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Robert</namePart>
<namePart type="family">Vacareanu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">George</namePart>
<namePart type="given">C.G.</namePart>
<namePart type="family">Barbosa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Enrique</namePart>
<namePart type="family">Noriega-Atala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gus</namePart>
<namePart type="family">Hahn-Powell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebecca</namePart>
<namePart type="family">Sharp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Valenzuela-Escárcega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mihai</namePart>
<namePart type="family">Surdeanu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: System Demonstrations</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hybrid: Seattle, Washington + Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose a system that assists a user in constructing transparent information extraction models, consisting of patterns (or rules) written in a declarative language, through program synthesis.Users of our system can specify their requirements through the use of examples,which are collected with a search interface.The rule-synthesis system proposes rule candidates and the results of applying them on a textual corpus; the user has the option to accept the candidate, request another option, or adjust the examples provided to the system.Through an interactive evaluation, we show that our approach generates high-precision rules even in a 1-shot setting. On a second evaluation on a widely-used relation extraction dataset (TACRED), our method generates rules that outperform considerably manually written patterns.Our code, demo, and documentation is available at https://clulab.github.io/odinsynth.</abstract>
<identifier type="citekey">vacareanu-etal-2022-human</identifier>
<identifier type="doi">10.18653/v1/2022.naacl-demo.8</identifier>
<location>
<url>https://aclanthology.org/2022.naacl-demo.8</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>64</start>
<end>70</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Human-machine Interface for Few-shot Rule Synthesis for Information Extraction
%A Vacareanu, Robert
%A Barbosa, George C.G.
%A Noriega-Atala, Enrique
%A Hahn-Powell, Gus
%A Sharp, Rebecca
%A Valenzuela-Escárcega, Marco A.
%A Surdeanu, Mihai
%S Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: System Demonstrations
%D 2022
%8 July
%I Association for Computational Linguistics
%C Hybrid: Seattle, Washington + Online
%F vacareanu-etal-2022-human
%X We propose a system that assists a user in constructing transparent information extraction models, consisting of patterns (or rules) written in a declarative language, through program synthesis.Users of our system can specify their requirements through the use of examples,which are collected with a search interface.The rule-synthesis system proposes rule candidates and the results of applying them on a textual corpus; the user has the option to accept the candidate, request another option, or adjust the examples provided to the system.Through an interactive evaluation, we show that our approach generates high-precision rules even in a 1-shot setting. On a second evaluation on a widely-used relation extraction dataset (TACRED), our method generates rules that outperform considerably manually written patterns.Our code, demo, and documentation is available at https://clulab.github.io/odinsynth.
%R 10.18653/v1/2022.naacl-demo.8
%U https://aclanthology.org/2022.naacl-demo.8
%U https://doi.org/10.18653/v1/2022.naacl-demo.8
%P 64-70
Markdown (Informal)
[A Human-machine Interface for Few-shot Rule Synthesis for Information Extraction](https://aclanthology.org/2022.naacl-demo.8) (Vacareanu et al., NAACL 2022)
ACL
- Robert Vacareanu, George C.G. Barbosa, Enrique Noriega-Atala, Gus Hahn-Powell, Rebecca Sharp, Marco A. Valenzuela-Escárcega, and Mihai Surdeanu. 2022. A Human-machine Interface for Few-shot Rule Synthesis for Information Extraction. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: System Demonstrations, pages 64–70, Hybrid: Seattle, Washington + Online. Association for Computational Linguistics.