@inproceedings{ogren-etal-2008-constructing,
title = "Constructing Evaluation Corpora for Automated Clinical Named Entity Recognition",
author = "Ogren, Philip and
Savova, Guergana and
Chute, Christopher",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Maegaard, Bente and
Mariani, Joseph and
Odijk, Jan and
Piperidis, Stelios and
Tapias, Daniel",
booktitle = "Proceedings of the Sixth International Conference on Language Resources and Evaluation ({LREC}'08)",
month = may,
year = "2008",
address = "Marrakech, Morocco",
publisher = "European Language Resources Association (ELRA)",
url = "http://www.lrec-conf.org/proceedings/lrec2008/pdf/796_paper.pdf",
abstract = "We report on the construction of a gold-standard dataset consisting of annotated clinical notes suitable for evaluating our biomedical named entity recognition system. The dataset is the result of consensus between four human annotators and contains 1,556 annotations on 160 clinical notes using 658 unique concept codes from SNOMED-CT corresponding to human disorders. Inter-annotator agreement was calculated on annotations from 100 of the documents for span (90.9{\%}), concept code (81.7{\%}), context (84.8{\%}), and status (86.0{\%}) agreement. Complete agreement for span, concept code, context, and status was 74.6{\%}. We found that creating a consensus set based on annotations from two independently-created annotation sets can reduce inter-annotator disagreement by 32.3{\%}. We found little benefit to pre-annotating the corpus with a third-party named entity recognizer.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ogren-etal-2008-constructing">
<titleInfo>
<title>Constructing Evaluation Corpora for Automated Clinical Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Philip</namePart>
<namePart type="family">Ogren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guergana</namePart>
<namePart type="family">Savova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Chute</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2008-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)</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">Khalid</namePart>
<namePart type="family">Choukri</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">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>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Tapias</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Marrakech, Morocco</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We report on the construction of a gold-standard dataset consisting of annotated clinical notes suitable for evaluating our biomedical named entity recognition system. The dataset is the result of consensus between four human annotators and contains 1,556 annotations on 160 clinical notes using 658 unique concept codes from SNOMED-CT corresponding to human disorders. Inter-annotator agreement was calculated on annotations from 100 of the documents for span (90.9%), concept code (81.7%), context (84.8%), and status (86.0%) agreement. Complete agreement for span, concept code, context, and status was 74.6%. We found that creating a consensus set based on annotations from two independently-created annotation sets can reduce inter-annotator disagreement by 32.3%. We found little benefit to pre-annotating the corpus with a third-party named entity recognizer.</abstract>
<identifier type="citekey">ogren-etal-2008-constructing</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/796_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Constructing Evaluation Corpora for Automated Clinical Named Entity Recognition
%A Ogren, Philip
%A Savova, Guergana
%A Chute, Christopher
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Odijk, Jan
%Y Piperidis, Stelios
%Y Tapias, Daniel
%S Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC’08)
%D 2008
%8 May
%I European Language Resources Association (ELRA)
%C Marrakech, Morocco
%F ogren-etal-2008-constructing
%X We report on the construction of a gold-standard dataset consisting of annotated clinical notes suitable for evaluating our biomedical named entity recognition system. The dataset is the result of consensus between four human annotators and contains 1,556 annotations on 160 clinical notes using 658 unique concept codes from SNOMED-CT corresponding to human disorders. Inter-annotator agreement was calculated on annotations from 100 of the documents for span (90.9%), concept code (81.7%), context (84.8%), and status (86.0%) agreement. Complete agreement for span, concept code, context, and status was 74.6%. We found that creating a consensus set based on annotations from two independently-created annotation sets can reduce inter-annotator disagreement by 32.3%. We found little benefit to pre-annotating the corpus with a third-party named entity recognizer.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/796_paper.pdf
Markdown (Informal)
[Constructing Evaluation Corpora for Automated Clinical Named Entity Recognition](http://www.lrec-conf.org/proceedings/lrec2008/pdf/796_paper.pdf) (Ogren et al., LREC 2008)
ACL