@inproceedings{llorca-etal-2023-meta,
title = "A Meta-dataset of {G}erman Medical Corpora: Harmonization of Annotations and Cross-corpus {NER} Evaluation",
author = "Llorca, Ignacio and
Borchert, Florian and
Schapranow, Matthieu-P.",
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-1.23",
doi = "10.18653/v1/2023.clinicalnlp-1.23",
pages = "171--181",
abstract = "Over the last years, an increasing number of publicly available, semantically annotated medical corpora have been released for the German language. While their annotations cover comparable semantic classes, the synergies of such efforts have not been explored, yet. This is due to substantial differences in the data schemas (syntax) and annotated entities (semantics), which hinder the creation of common meta-datasets. For instance, it is unclear whether named entity recognition (NER) taggers trained on one or more of such datasets are useful to detect entities in any of the other datasets. In this work, we create harmonized versions of German medical corpora using the BigBIO framework, and make them available to the community. Using these as a meta-dataset, we perform a series of cross-corpus evaluation experiments on two settings of aligned labels. These consist in fine-tuning various pre-trained Transformers on different combinations of training sets, and testing them against each dataset separately. We find that a) trained NER models generalize poorly, with F1 scores dropping approx. 20 pp. on unseen test data, and b) current pre-trained Transformer models for the German language do not systematically alleviate this issue. However, our results suggest that models benefit from additional training corpora in most cases, even if these belong to different medical fields or text genres.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="llorca-etal-2023-meta">
<titleInfo>
<title>A Meta-dataset of German Medical Corpora: Harmonization of Annotations and Cross-corpus NER Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ignacio</namePart>
<namePart type="family">Llorca</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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">Matthieu-P.</namePart>
<namePart type="family">Schapranow</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>Over the last years, an increasing number of publicly available, semantically annotated medical corpora have been released for the German language. While their annotations cover comparable semantic classes, the synergies of such efforts have not been explored, yet. This is due to substantial differences in the data schemas (syntax) and annotated entities (semantics), which hinder the creation of common meta-datasets. For instance, it is unclear whether named entity recognition (NER) taggers trained on one or more of such datasets are useful to detect entities in any of the other datasets. In this work, we create harmonized versions of German medical corpora using the BigBIO framework, and make them available to the community. Using these as a meta-dataset, we perform a series of cross-corpus evaluation experiments on two settings of aligned labels. These consist in fine-tuning various pre-trained Transformers on different combinations of training sets, and testing them against each dataset separately. We find that a) trained NER models generalize poorly, with F1 scores dropping approx. 20 pp. on unseen test data, and b) current pre-trained Transformer models for the German language do not systematically alleviate this issue. However, our results suggest that models benefit from additional training corpora in most cases, even if these belong to different medical fields or text genres.</abstract>
<identifier type="citekey">llorca-etal-2023-meta</identifier>
<identifier type="doi">10.18653/v1/2023.clinicalnlp-1.23</identifier>
<location>
<url>https://aclanthology.org/2023.clinicalnlp-1.23</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>171</start>
<end>181</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Meta-dataset of German Medical Corpora: Harmonization of Annotations and Cross-corpus NER Evaluation
%A Llorca, Ignacio
%A Borchert, Florian
%A Schapranow, Matthieu-P.
%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 llorca-etal-2023-meta
%X Over the last years, an increasing number of publicly available, semantically annotated medical corpora have been released for the German language. While their annotations cover comparable semantic classes, the synergies of such efforts have not been explored, yet. This is due to substantial differences in the data schemas (syntax) and annotated entities (semantics), which hinder the creation of common meta-datasets. For instance, it is unclear whether named entity recognition (NER) taggers trained on one or more of such datasets are useful to detect entities in any of the other datasets. In this work, we create harmonized versions of German medical corpora using the BigBIO framework, and make them available to the community. Using these as a meta-dataset, we perform a series of cross-corpus evaluation experiments on two settings of aligned labels. These consist in fine-tuning various pre-trained Transformers on different combinations of training sets, and testing them against each dataset separately. We find that a) trained NER models generalize poorly, with F1 scores dropping approx. 20 pp. on unseen test data, and b) current pre-trained Transformer models for the German language do not systematically alleviate this issue. However, our results suggest that models benefit from additional training corpora in most cases, even if these belong to different medical fields or text genres.
%R 10.18653/v1/2023.clinicalnlp-1.23
%U https://aclanthology.org/2023.clinicalnlp-1.23
%U https://doi.org/10.18653/v1/2023.clinicalnlp-1.23
%P 171-181
Markdown (Informal)
[A Meta-dataset of German Medical Corpora: Harmonization of Annotations and Cross-corpus NER Evaluation](https://aclanthology.org/2023.clinicalnlp-1.23) (Llorca et al., ClinicalNLP 2023)
ACL