@inproceedings{kolluru-etal-2020-imojie,
title = "{IM}o{JIE}: Iterative Memory-Based Joint Open Information Extraction",
author = "Kolluru, Keshav and
Aggarwal, Samarth and
Rathore, Vipul and
Mausam and
Chakrabarti, Soumen",
editor = "Jurafsky, Dan and
Chai, Joyce and
Schluter, Natalie and
Tetreault, Joel",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.521/",
doi = "10.18653/v1/2020.acl-main.521",
pages = "5871--5886",
abstract = "While traditional systems for Open Information Extraction were statistical and rule-based, recently neural models have been introduced for the task. Our work builds upon CopyAttention, a sequence generation OpenIE model (Cui et. al. 18). Our analysis reveals that CopyAttention produces a constant number of extractions per sentence, and its extracted tuples often express redundant information. We present IMoJIE, an extension to CopyAttention, which produces the next extraction conditioned on all previously extracted tuples. This approach overcomes both shortcomings of CopyAttention, resulting in a variable number of diverse extractions per sentence. We train IMoJIE on training data bootstrapped from extractions of several non-neural systems, which have been automatically filtered to reduce redundancy and noise. IMoJIE outperforms CopyAttention by about 18 F1 pts, and a BERT-based strong baseline by 2 F1 pts, establishing a new state of the art for the task."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kolluru-etal-2020-imojie">
<titleInfo>
<title>IMoJIE: Iterative Memory-Based Joint Open Information Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Keshav</namePart>
<namePart type="family">Kolluru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samarth</namePart>
<namePart type="family">Aggarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vipul</namePart>
<namePart type="family">Rathore</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name>
<namePart>Mausam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Soumen</namePart>
<namePart type="family">Chakrabarti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While traditional systems for Open Information Extraction were statistical and rule-based, recently neural models have been introduced for the task. Our work builds upon CopyAttention, a sequence generation OpenIE model (Cui et. al. 18). Our analysis reveals that CopyAttention produces a constant number of extractions per sentence, and its extracted tuples often express redundant information. We present IMoJIE, an extension to CopyAttention, which produces the next extraction conditioned on all previously extracted tuples. This approach overcomes both shortcomings of CopyAttention, resulting in a variable number of diverse extractions per sentence. We train IMoJIE on training data bootstrapped from extractions of several non-neural systems, which have been automatically filtered to reduce redundancy and noise. IMoJIE outperforms CopyAttention by about 18 F1 pts, and a BERT-based strong baseline by 2 F1 pts, establishing a new state of the art for the task.</abstract>
<identifier type="citekey">kolluru-etal-2020-imojie</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.521</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.521/</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>5871</start>
<end>5886</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T IMoJIE: Iterative Memory-Based Joint Open Information Extraction
%A Kolluru, Keshav
%A Aggarwal, Samarth
%A Rathore, Vipul
%A Chakrabarti, Soumen
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%A Mausam
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F kolluru-etal-2020-imojie
%X While traditional systems for Open Information Extraction were statistical and rule-based, recently neural models have been introduced for the task. Our work builds upon CopyAttention, a sequence generation OpenIE model (Cui et. al. 18). Our analysis reveals that CopyAttention produces a constant number of extractions per sentence, and its extracted tuples often express redundant information. We present IMoJIE, an extension to CopyAttention, which produces the next extraction conditioned on all previously extracted tuples. This approach overcomes both shortcomings of CopyAttention, resulting in a variable number of diverse extractions per sentence. We train IMoJIE on training data bootstrapped from extractions of several non-neural systems, which have been automatically filtered to reduce redundancy and noise. IMoJIE outperforms CopyAttention by about 18 F1 pts, and a BERT-based strong baseline by 2 F1 pts, establishing a new state of the art for the task.
%R 10.18653/v1/2020.acl-main.521
%U https://aclanthology.org/2020.acl-main.521/
%U https://doi.org/10.18653/v1/2020.acl-main.521
%P 5871-5886
Markdown (Informal)
[IMoJIE: Iterative Memory-Based Joint Open Information Extraction](https://aclanthology.org/2020.acl-main.521/) (Kolluru et al., ACL 2020)
- IMoJIE: Iterative Memory-Based Joint Open Information Extraction (Kolluru et al., ACL 2020)
ACL
- Keshav Kolluru, Samarth Aggarwal, Vipul Rathore, Mausam, and Soumen Chakrabarti. 2020. IMoJIE: Iterative Memory-Based Joint Open Information Extraction. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5871–5886, Online. Association for Computational Linguistics.