@inproceedings{ivanova-etal-2022-comparing,
title = "Comparing Annotated Datasets for Named Entity Recognition in {E}nglish Literature",
author = "Ivanova, Rositsa and
van Erp, Marieke and
Kirrane, Sabrina",
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-1.404",
pages = "3788--3797",
abstract = "The growing interest in named entity recognition (NER) in various domains has led to the creation of different benchmark datasets, often with slightly different annotation guidelines. To better understand the different NER benchmark datasets for the domain of English literature and their impact on the evaluation of NER tools, we analyse two existing annotated datasets and create two additional gold standard datasets. Following on from this, we evaluate the performance of two NER tools, one domain-specific and one general-purpose NER tool, using the four gold standards, and analyse the sources for the differences in the measured performance. Our results show that the performance of the two tools varies significantly depending on the gold standard used for the individual evaluations.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ivanova-etal-2022-comparing">
<titleInfo>
<title>Comparing Annotated Datasets for Named Entity Recognition in English Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rositsa</namePart>
<namePart type="family">Ivanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marieke</namePart>
<namePart type="family">van Erp</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabrina</namePart>
<namePart type="family">Kirrane</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>The growing interest in named entity recognition (NER) in various domains has led to the creation of different benchmark datasets, often with slightly different annotation guidelines. To better understand the different NER benchmark datasets for the domain of English literature and their impact on the evaluation of NER tools, we analyse two existing annotated datasets and create two additional gold standard datasets. Following on from this, we evaluate the performance of two NER tools, one domain-specific and one general-purpose NER tool, using the four gold standards, and analyse the sources for the differences in the measured performance. Our results show that the performance of the two tools varies significantly depending on the gold standard used for the individual evaluations.</abstract>
<identifier type="citekey">ivanova-etal-2022-comparing</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.404</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>3788</start>
<end>3797</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Comparing Annotated Datasets for Named Entity Recognition in English Literature
%A Ivanova, Rositsa
%A van Erp, Marieke
%A Kirrane, Sabrina
%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 ivanova-etal-2022-comparing
%X The growing interest in named entity recognition (NER) in various domains has led to the creation of different benchmark datasets, often with slightly different annotation guidelines. To better understand the different NER benchmark datasets for the domain of English literature and their impact on the evaluation of NER tools, we analyse two existing annotated datasets and create two additional gold standard datasets. Following on from this, we evaluate the performance of two NER tools, one domain-specific and one general-purpose NER tool, using the four gold standards, and analyse the sources for the differences in the measured performance. Our results show that the performance of the two tools varies significantly depending on the gold standard used for the individual evaluations.
%U https://aclanthology.org/2022.lrec-1.404
%P 3788-3797
Markdown (Informal)
[Comparing Annotated Datasets for Named Entity Recognition in English Literature](https://aclanthology.org/2022.lrec-1.404) (Ivanova et al., LREC 2022)
ACL