@inproceedings{kokkinakis-2008-semantically,
title = "A Semantically Annotated {S}wedish Medical Corpus",
author = "Kokkinakis, Dimitrios",
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/15_paper.pdf",
abstract = "With the information overload in the life sciences there is an increasing need for annotated corpora, particularly with biological and biomedical entities, which is the driving force for data-driven language processing applications and the empirical approach to language study. Inspired by the work in the GENIA Corpus, which is one of the very few of such corpora, extensively used in the biomedical field, and in order to fulfil the needs of our research, we have collected a Swedish medical corpus, the MEDLEX Corpus. MEDLEX is a large structurally and linguistically annotated document collection, consisting of a variety of text documents related to various medical text subfields, and does not focus at a particular medical genre, due to the lack of large Swedish resources within a particular medical subdomain. Out of this collection we selected 300 documents which were manually examined by two human experts who inspected, corrected and/or accordingly modified the automatically provided annotations according to a set of provided labelling guidelines. The annotations consist of medical terminology provided by the Swedish and English MeSH{\copyright} (Medical Subject Headings) thesauri as well as named entity labels provided by an enhanced named entity recognition software.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kokkinakis-2008-semantically">
<titleInfo>
<title>A Semantically Annotated Swedish Medical Corpus</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dimitrios</namePart>
<namePart type="family">Kokkinakis</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>With the information overload in the life sciences there is an increasing need for annotated corpora, particularly with biological and biomedical entities, which is the driving force for data-driven language processing applications and the empirical approach to language study. Inspired by the work in the GENIA Corpus, which is one of the very few of such corpora, extensively used in the biomedical field, and in order to fulfil the needs of our research, we have collected a Swedish medical corpus, the MEDLEX Corpus. MEDLEX is a large structurally and linguistically annotated document collection, consisting of a variety of text documents related to various medical text subfields, and does not focus at a particular medical genre, due to the lack of large Swedish resources within a particular medical subdomain. Out of this collection we selected 300 documents which were manually examined by two human experts who inspected, corrected and/or accordingly modified the automatically provided annotations according to a set of provided labelling guidelines. The annotations consist of medical terminology provided by the Swedish and English MeSH\copyright (Medical Subject Headings) thesauri as well as named entity labels provided by an enhanced named entity recognition software.</abstract>
<identifier type="citekey">kokkinakis-2008-semantically</identifier>
<location>
<url>http://www.lrec-conf.org/proceedings/lrec2008/pdf/15_paper.pdf</url>
</location>
<part>
<date>2008-05</date>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Semantically Annotated Swedish Medical Corpus
%A Kokkinakis, Dimitrios
%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 kokkinakis-2008-semantically
%X With the information overload in the life sciences there is an increasing need for annotated corpora, particularly with biological and biomedical entities, which is the driving force for data-driven language processing applications and the empirical approach to language study. Inspired by the work in the GENIA Corpus, which is one of the very few of such corpora, extensively used in the biomedical field, and in order to fulfil the needs of our research, we have collected a Swedish medical corpus, the MEDLEX Corpus. MEDLEX is a large structurally and linguistically annotated document collection, consisting of a variety of text documents related to various medical text subfields, and does not focus at a particular medical genre, due to the lack of large Swedish resources within a particular medical subdomain. Out of this collection we selected 300 documents which were manually examined by two human experts who inspected, corrected and/or accordingly modified the automatically provided annotations according to a set of provided labelling guidelines. The annotations consist of medical terminology provided by the Swedish and English MeSH\copyright (Medical Subject Headings) thesauri as well as named entity labels provided by an enhanced named entity recognition software.
%U http://www.lrec-conf.org/proceedings/lrec2008/pdf/15_paper.pdf
Markdown (Informal)
[A Semantically Annotated Swedish Medical Corpus](http://www.lrec-conf.org/proceedings/lrec2008/pdf/15_paper.pdf) (Kokkinakis, LREC 2008)
ACL
- Dimitrios Kokkinakis. 2008. A Semantically Annotated Swedish Medical Corpus. In Proceedings of the Sixth International Conference on Language Resources and Evaluation (LREC'08), Marrakech, Morocco. European Language Resources Association (ELRA).