@inproceedings{hofenbitzer-etal-2026-developing,
title = "Developing the {G}erman Medical Text Corpus ({G}e{MT}e{X}): Legal Compliance and Semantic Enrichment",
author = {Hofenbitzer, Justin and
Lohr, Christina and
Riedel, Andrea and
Kiser, Rebekka and
Shutsko, Aliaksandra and
Abdelmalak, Abanoub and
Kl{\"u}gl, Peter and
Romberg, Jutta and
Riepenhausen, Sarah and
Schechner, Miriam and
Faller, Jakob and
Meineke, Frank and
Modersohn, Luise and
L{\"o}ffler, Markus and
Fluck, Juliane and
Hahn, Udo and
Schulz, Stefan and
Boeker, Martin},
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.122/",
doi = "10.63317/4eqiegnqbu96",
pages = "1571--1584",
abstract = "GeMTeX is a large-scale German Medical Text Corpus project with the goal to publish a clinical national reference corpus. The resource is currently under construction and comprises, as of February 2026, more than 15k clinical documents (20M tokens) from six German university hospitals. When building GeMTeX, attention was paid to comply with European regulatory requirements. In phase I, patients were asked to allow reuse of their clinical documents based on the legal foundation of an ``informed consent''. In phase II, consented documents from six major clinical sites in Germany underwent a thorough de-identification process. In phase III, we currently enrich this unlocked dataset with semantic information from the clinical domain. This annotation process is guided by Snomed CT, which supports to directly ground expressions within clinical documents in a worldwide shared medical documentation and ontology standard. The resource is currently under active development and is accessible upon request under controlled access conditions. We refer interested researchers to visit \url{https://kiinformatik.mri.tum.de/en/gemtex} or reach out via gemtex.mi@mh.tum.de."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hofenbitzer-etal-2026-developing">
<titleInfo>
<title>Developing the German Medical Text Corpus (GeMTeX): Legal Compliance and Semantic Enrichment</title>
</titleInfo>
<name type="personal">
<namePart type="given">Justin</namePart>
<namePart type="family">Hofenbitzer</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">Andrea</namePart>
<namePart type="family">Riedel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rebekka</namePart>
<namePart type="family">Kiser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aliaksandra</namePart>
<namePart type="family">Shutsko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abanoub</namePart>
<namePart type="family">Abdelmalak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peter</namePart>
<namePart type="family">Klügl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jutta</namePart>
<namePart type="family">Romberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Riepenhausen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miriam</namePart>
<namePart type="family">Schechner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jakob</namePart>
<namePart type="family">Faller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frank</namePart>
<namePart type="family">Meineke</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">Markus</namePart>
<namePart type="family">Löffler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juliane</namePart>
<namePart type="family">Fluck</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">Stefan</namePart>
<namePart type="family">Schulz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Martin</namePart>
<namePart type="family">Boeker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<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">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>GeMTeX is a large-scale German Medical Text Corpus project with the goal to publish a clinical national reference corpus. The resource is currently under construction and comprises, as of February 2026, more than 15k clinical documents (20M tokens) from six German university hospitals. When building GeMTeX, attention was paid to comply with European regulatory requirements. In phase I, patients were asked to allow reuse of their clinical documents based on the legal foundation of an “informed consent”. In phase II, consented documents from six major clinical sites in Germany underwent a thorough de-identification process. In phase III, we currently enrich this unlocked dataset with semantic information from the clinical domain. This annotation process is guided by Snomed CT, which supports to directly ground expressions within clinical documents in a worldwide shared medical documentation and ontology standard. The resource is currently under active development and is accessible upon request under controlled access conditions. We refer interested researchers to visit https://kiinformatik.mri.tum.de/en/gemtex or reach out via gemtex.mi@mh.tum.de.</abstract>
<identifier type="citekey">hofenbitzer-etal-2026-developing</identifier>
<identifier type="doi">10.63317/4eqiegnqbu96</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.122/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1571</start>
<end>1584</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Developing the German Medical Text Corpus (GeMTeX): Legal Compliance and Semantic Enrichment
%A Hofenbitzer, Justin
%A Lohr, Christina
%A Riedel, Andrea
%A Kiser, Rebekka
%A Shutsko, Aliaksandra
%A Abdelmalak, Abanoub
%A Klügl, Peter
%A Romberg, Jutta
%A Riepenhausen, Sarah
%A Schechner, Miriam
%A Faller, Jakob
%A Meineke, Frank
%A Modersohn, Luise
%A Löffler, Markus
%A Fluck, Juliane
%A Hahn, Udo
%A Schulz, Stefan
%A Boeker, Martin
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F hofenbitzer-etal-2026-developing
%X GeMTeX is a large-scale German Medical Text Corpus project with the goal to publish a clinical national reference corpus. The resource is currently under construction and comprises, as of February 2026, more than 15k clinical documents (20M tokens) from six German university hospitals. When building GeMTeX, attention was paid to comply with European regulatory requirements. In phase I, patients were asked to allow reuse of their clinical documents based on the legal foundation of an “informed consent”. In phase II, consented documents from six major clinical sites in Germany underwent a thorough de-identification process. In phase III, we currently enrich this unlocked dataset with semantic information from the clinical domain. This annotation process is guided by Snomed CT, which supports to directly ground expressions within clinical documents in a worldwide shared medical documentation and ontology standard. The resource is currently under active development and is accessible upon request under controlled access conditions. We refer interested researchers to visit https://kiinformatik.mri.tum.de/en/gemtex or reach out via gemtex.mi@mh.tum.de.
%R 10.63317/4eqiegnqbu96
%U https://aclanthology.org/2026.lrec-1.122/
%U https://doi.org/10.63317/4eqiegnqbu96
%P 1571-1584
Markdown (Informal)
[Developing the German Medical Text Corpus (GeMTeX): Legal Compliance and Semantic Enrichment](https://aclanthology.org/2026.lrec-1.122/) (Hofenbitzer et al., LREC 2026)
ACL
- Justin Hofenbitzer, Christina Lohr, Andrea Riedel, Rebekka Kiser, Aliaksandra Shutsko, Abanoub Abdelmalak, Peter Klügl, Jutta Romberg, Sarah Riepenhausen, Miriam Schechner, Jakob Faller, Frank Meineke, Luise Modersohn, Markus Löffler, Juliane Fluck, Udo Hahn, Stefan Schulz, and Martin Boeker. 2026. Developing the German Medical Text Corpus (GeMTeX): Legal Compliance and Semantic Enrichment. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 1571–1584, Palma de Mallorca, Spain. ELRA Language Resource Association.