@inproceedings{liang-etal-2023-cross,
title = "Cross-domain {G}erman Medical Named Entity Recognition using a Pre-Trained Language Model and Unified Medical Semantic Types",
author = "Liang, Siting and
Hartmann, Mareike and
Sonntag, Daniel",
editor = "Naumann, Tristan and
Ben Abacha, Asma and
Bethard, Steven and
Roberts, Kirk and
Rumshisky, Anna",
booktitle = "Proceedings of the 5th Clinical Natural Language Processing Workshop",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.clinicalnlp-1.31",
doi = "10.18653/v1/2023.clinicalnlp-1.31",
pages = "259--271",
abstract = "Information extraction from clinical text has the potential to facilitate clinical research and personalized clinical care, but annotating large amounts of data for each set of target tasks is prohibitive. We present a German medical Named Entity Recognition (NER) system capable of cross-domain knowledge transferring. The system builds on a pre-trained German language model and a token-level binary classifier, employing semantic types sourced from the Unified Medical Language System (UMLS) as entity labels to identify corresponding entity spans within the input text. To enhance the system{'}s performance and robustness, we pre-train it using a medical literature corpus that incorporates UMLS semantic term annotations. We evaluate the system{'}s effectiveness on two German annotated datasets obtained from different clinics in zero- and few-shot settings. The results show that our approach outperforms task-specific Condition Random Fields (CRF) classifiers in terms of accuracy. Our work contributes to developing robust and transparent German medical NER models that can support the extraction of information from various clinical texts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liang-etal-2023-cross">
<titleInfo>
<title>Cross-domain German Medical Named Entity Recognition using a Pre-Trained Language Model and Unified Medical Semantic Types</title>
</titleInfo>
<name type="personal">
<namePart type="given">Siting</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mareike</namePart>
<namePart type="family">Hartmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Sonntag</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Clinical Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Naumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="family">Ben Abacha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Information extraction from clinical text has the potential to facilitate clinical research and personalized clinical care, but annotating large amounts of data for each set of target tasks is prohibitive. We present a German medical Named Entity Recognition (NER) system capable of cross-domain knowledge transferring. The system builds on a pre-trained German language model and a token-level binary classifier, employing semantic types sourced from the Unified Medical Language System (UMLS) as entity labels to identify corresponding entity spans within the input text. To enhance the system’s performance and robustness, we pre-train it using a medical literature corpus that incorporates UMLS semantic term annotations. We evaluate the system’s effectiveness on two German annotated datasets obtained from different clinics in zero- and few-shot settings. The results show that our approach outperforms task-specific Condition Random Fields (CRF) classifiers in terms of accuracy. Our work contributes to developing robust and transparent German medical NER models that can support the extraction of information from various clinical texts.</abstract>
<identifier type="citekey">liang-etal-2023-cross</identifier>
<identifier type="doi">10.18653/v1/2023.clinicalnlp-1.31</identifier>
<location>
<url>https://aclanthology.org/2023.clinicalnlp-1.31</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>259</start>
<end>271</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-domain German Medical Named Entity Recognition using a Pre-Trained Language Model and Unified Medical Semantic Types
%A Liang, Siting
%A Hartmann, Mareike
%A Sonntag, Daniel
%Y Naumann, Tristan
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Roberts, Kirk
%Y Rumshisky, Anna
%S Proceedings of the 5th Clinical Natural Language Processing Workshop
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F liang-etal-2023-cross
%X Information extraction from clinical text has the potential to facilitate clinical research and personalized clinical care, but annotating large amounts of data for each set of target tasks is prohibitive. We present a German medical Named Entity Recognition (NER) system capable of cross-domain knowledge transferring. The system builds on a pre-trained German language model and a token-level binary classifier, employing semantic types sourced from the Unified Medical Language System (UMLS) as entity labels to identify corresponding entity spans within the input text. To enhance the system’s performance and robustness, we pre-train it using a medical literature corpus that incorporates UMLS semantic term annotations. We evaluate the system’s effectiveness on two German annotated datasets obtained from different clinics in zero- and few-shot settings. The results show that our approach outperforms task-specific Condition Random Fields (CRF) classifiers in terms of accuracy. Our work contributes to developing robust and transparent German medical NER models that can support the extraction of information from various clinical texts.
%R 10.18653/v1/2023.clinicalnlp-1.31
%U https://aclanthology.org/2023.clinicalnlp-1.31
%U https://doi.org/10.18653/v1/2023.clinicalnlp-1.31
%P 259-271
Markdown (Informal)
[Cross-domain German Medical Named Entity Recognition using a Pre-Trained Language Model and Unified Medical Semantic Types](https://aclanthology.org/2023.clinicalnlp-1.31) (Liang et al., ClinicalNLP 2023)
ACL