@inproceedings{friedrich-etal-2022-annie,
title = "{A}nn{IE}: An Annotation Platform for Constructing Complete Open Information Extraction Benchmark",
author = "Friedrich, Niklas and
Gashteovski, Kiril and
Yu, Mingying and
Kotnis, Bhushan and
Lawrence, Carolin and
Niepert, Mathias and
Glava{\v{s}}, Goran",
editor = "Basile, Valerio and
Kozareva, Zornitsa and
Stajner, Sanja",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-demo.5/",
doi = "10.18653/v1/2022.acl-demo.5",
pages = "44--60",
abstract = "Open Information Extraction (OIE) is the task of extracting facts from sentences in the form of relations and their corresponding arguments in schema-free manner. Intrinsic performance of OIE systems is difficult to measure due to the incompleteness of existing OIE benchmarks: ground truth extractions do not group all acceptable surface realizations of the same fact that can be extracted from a sentence. To measure performance of OIE systems more realistically, it is necessary to manually annotate complete facts (i.e., clusters of all acceptable surface realizations of the same fact) from input sentences. We propose AnnIE: an interactive annotation platform that facilitates such challenging annotation tasks and supports creation of complete fact-oriented OIE evaluation benchmarks. AnnIE is modular and flexible in order to support different use case scenarios (i.e., benchmarks covering different types of facts) and different languages. We use AnnIE to build two complete OIE benchmarks: one with verb-mediated facts and another with facts encompassing named entities. We evaluate several OIE systems on our complete benchmarks created with AnnIE. We publicly release AnnIE (and all gold datasets generated with it) under non-restrictive license."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="friedrich-etal-2022-annie">
<titleInfo>
<title>AnnIE: An Annotation Platform for Constructing Complete Open Information Extraction Benchmark</title>
</titleInfo>
<name type="personal">
<namePart type="given">Niklas</namePart>
<namePart type="family">Friedrich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kiril</namePart>
<namePart type="family">Gashteovski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingying</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bhushan</namePart>
<namePart type="family">Kotnis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Carolin</namePart>
<namePart type="family">Lawrence</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mathias</namePart>
<namePart type="family">Niepert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Goran</namePart>
<namePart type="family">Glavaš</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Valerio</namePart>
<namePart type="family">Basile</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanja</namePart>
<namePart type="family">Stajner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Open Information Extraction (OIE) is the task of extracting facts from sentences in the form of relations and their corresponding arguments in schema-free manner. Intrinsic performance of OIE systems is difficult to measure due to the incompleteness of existing OIE benchmarks: ground truth extractions do not group all acceptable surface realizations of the same fact that can be extracted from a sentence. To measure performance of OIE systems more realistically, it is necessary to manually annotate complete facts (i.e., clusters of all acceptable surface realizations of the same fact) from input sentences. We propose AnnIE: an interactive annotation platform that facilitates such challenging annotation tasks and supports creation of complete fact-oriented OIE evaluation benchmarks. AnnIE is modular and flexible in order to support different use case scenarios (i.e., benchmarks covering different types of facts) and different languages. We use AnnIE to build two complete OIE benchmarks: one with verb-mediated facts and another with facts encompassing named entities. We evaluate several OIE systems on our complete benchmarks created with AnnIE. We publicly release AnnIE (and all gold datasets generated with it) under non-restrictive license.</abstract>
<identifier type="citekey">friedrich-etal-2022-annie</identifier>
<identifier type="doi">10.18653/v1/2022.acl-demo.5</identifier>
<location>
<url>https://aclanthology.org/2022.acl-demo.5/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>44</start>
<end>60</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AnnIE: An Annotation Platform for Constructing Complete Open Information Extraction Benchmark
%A Friedrich, Niklas
%A Gashteovski, Kiril
%A Yu, Mingying
%A Kotnis, Bhushan
%A Lawrence, Carolin
%A Niepert, Mathias
%A Glavaš, Goran
%Y Basile, Valerio
%Y Kozareva, Zornitsa
%Y Stajner, Sanja
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F friedrich-etal-2022-annie
%X Open Information Extraction (OIE) is the task of extracting facts from sentences in the form of relations and their corresponding arguments in schema-free manner. Intrinsic performance of OIE systems is difficult to measure due to the incompleteness of existing OIE benchmarks: ground truth extractions do not group all acceptable surface realizations of the same fact that can be extracted from a sentence. To measure performance of OIE systems more realistically, it is necessary to manually annotate complete facts (i.e., clusters of all acceptable surface realizations of the same fact) from input sentences. We propose AnnIE: an interactive annotation platform that facilitates such challenging annotation tasks and supports creation of complete fact-oriented OIE evaluation benchmarks. AnnIE is modular and flexible in order to support different use case scenarios (i.e., benchmarks covering different types of facts) and different languages. We use AnnIE to build two complete OIE benchmarks: one with verb-mediated facts and another with facts encompassing named entities. We evaluate several OIE systems on our complete benchmarks created with AnnIE. We publicly release AnnIE (and all gold datasets generated with it) under non-restrictive license.
%R 10.18653/v1/2022.acl-demo.5
%U https://aclanthology.org/2022.acl-demo.5/
%U https://doi.org/10.18653/v1/2022.acl-demo.5
%P 44-60
Markdown (Informal)
[AnnIE: An Annotation Platform for Constructing Complete Open Information Extraction Benchmark](https://aclanthology.org/2022.acl-demo.5/) (Friedrich et al., ACL 2022)
ACL