@inproceedings{borchert-etal-2020-ggponc,
title = "{GGPONC}: A Corpus of {G}erman Medical Text with Rich Metadata Based on Clinical Practice Guidelines",
author = "Borchert, Florian and
Lohr, Christina and
Modersohn, Luise and
Langer, Thomas and
Follmann, Markus and
Sachs, Jan Philipp and
Hahn, Udo and
Schapranow, Matthieu-P.",
editor = "Holderness, Eben and
Jimeno Yepes, Antonio and
Lavelli, Alberto and
Minard, Anne-Lyse and
Pustejovsky, James and
Rinaldi, Fabio",
booktitle = "Proceedings of the 11th International Workshop on Health Text Mining and Information Analysis",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.louhi-1.5/",
doi = "10.18653/v1/2020.louhi-1.5",
pages = "38--48",
abstract = "The lack of publicly accessible text corpora is a major obstacle for progress in natural language processing. For medical applications, unfortunately, all language communities other than English are low-resourced. In this work, we present GGPONC (German Guideline Program in Oncology NLP Corpus), a freely dis tributable German language corpus based on clinical practice guidelines for oncology. This corpus is one of the largest ever built from German medical documents. Unlike clinical documents, clinical guidelines do not contain any patient-related information and can therefore be used without data protection restrictions. Moreover, GGPONC is the first corpus for the German language covering diverse conditions in a large medical subfield and provides a variety of metadata, such as literature references and evidence levels. By applying and evaluating existing medical information extraction pipelines for German text, we are able to draw comparisons for the use of medical language to other corpora, medical and non-medical ones."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="borchert-etal-2020-ggponc">
<titleInfo>
<title>GGPONC: A Corpus of German Medical Text with Rich Metadata Based on Clinical Practice Guidelines</title>
</titleInfo>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Borchert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christina</namePart>
<namePart type="family">Lohr</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luise</namePart>
<namePart type="family">Modersohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Langer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Markus</namePart>
<namePart type="family">Follmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="given">Philipp</namePart>
<namePart type="family">Sachs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Udo</namePart>
<namePart type="family">Hahn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthieu-P.</namePart>
<namePart type="family">Schapranow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 11th International Workshop on Health Text Mining and Information Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eben</namePart>
<namePart type="family">Holderness</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Jimeno Yepes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Lavelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anne-Lyse</namePart>
<namePart type="family">Minard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Pustejovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="family">Rinaldi</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>The lack of publicly accessible text corpora is a major obstacle for progress in natural language processing. For medical applications, unfortunately, all language communities other than English are low-resourced. In this work, we present GGPONC (German Guideline Program in Oncology NLP Corpus), a freely dis tributable German language corpus based on clinical practice guidelines for oncology. This corpus is one of the largest ever built from German medical documents. Unlike clinical documents, clinical guidelines do not contain any patient-related information and can therefore be used without data protection restrictions. Moreover, GGPONC is the first corpus for the German language covering diverse conditions in a large medical subfield and provides a variety of metadata, such as literature references and evidence levels. By applying and evaluating existing medical information extraction pipelines for German text, we are able to draw comparisons for the use of medical language to other corpora, medical and non-medical ones.</abstract>
<identifier type="citekey">borchert-etal-2020-ggponc</identifier>
<identifier type="doi">10.18653/v1/2020.louhi-1.5</identifier>
<location>
<url>https://aclanthology.org/2020.louhi-1.5/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>38</start>
<end>48</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GGPONC: A Corpus of German Medical Text with Rich Metadata Based on Clinical Practice Guidelines
%A Borchert, Florian
%A Lohr, Christina
%A Modersohn, Luise
%A Langer, Thomas
%A Follmann, Markus
%A Sachs, Jan Philipp
%A Hahn, Udo
%A Schapranow, Matthieu-P.
%Y Holderness, Eben
%Y Jimeno Yepes, Antonio
%Y Lavelli, Alberto
%Y Minard, Anne-Lyse
%Y Pustejovsky, James
%Y Rinaldi, Fabio
%S Proceedings of the 11th International Workshop on Health Text Mining and Information Analysis
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F borchert-etal-2020-ggponc
%X The lack of publicly accessible text corpora is a major obstacle for progress in natural language processing. For medical applications, unfortunately, all language communities other than English are low-resourced. In this work, we present GGPONC (German Guideline Program in Oncology NLP Corpus), a freely dis tributable German language corpus based on clinical practice guidelines for oncology. This corpus is one of the largest ever built from German medical documents. Unlike clinical documents, clinical guidelines do not contain any patient-related information and can therefore be used without data protection restrictions. Moreover, GGPONC is the first corpus for the German language covering diverse conditions in a large medical subfield and provides a variety of metadata, such as literature references and evidence levels. By applying and evaluating existing medical information extraction pipelines for German text, we are able to draw comparisons for the use of medical language to other corpora, medical and non-medical ones.
%R 10.18653/v1/2020.louhi-1.5
%U https://aclanthology.org/2020.louhi-1.5/
%U https://doi.org/10.18653/v1/2020.louhi-1.5
%P 38-48
Markdown (Informal)
[GGPONC: A Corpus of German Medical Text with Rich Metadata Based on Clinical Practice Guidelines](https://aclanthology.org/2020.louhi-1.5/) (Borchert et al., Louhi 2020)
ACL