@inproceedings{macphail-etal-2024-evaluating,
title = "Evaluating the Robustness of Adverse Drug Event Classification Models using Templates",
author = {MacPhail, Dorothea and
Harbecke, David and
Raithel, Lisa and
M{\"o}ller, Sebastian},
editor = "Demner-Fushman, Dina and
Ananiadou, Sophia and
Miwa, Makoto and
Roberts, Kirk and
Tsujii, Junichi",
booktitle = "Proceedings of the 23rd Workshop on Biomedical Natural Language Processing",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.bionlp-1.3",
doi = "10.18653/v1/2024.bionlp-1.3",
pages = "25--38",
abstract = "An adverse drug effect (ADE) is any harmful event resulting from medical drug treatment. Despite their importance, ADEs are often under-reported in official channels. Some research has therefore turned to detecting discussions of ADEs in social media. Impressive results have been achieved in various attempts to detect ADEs. In a high-stakes domain such as medicine, however, an in-depth evaluation of a model{'}s abilities is crucial. We address the issue of thorough performance evaluation in detecting ADEs with hand-crafted templates for four capabilities, temporal order, negation, sentiment and beneficial effect. We find that models with similar performance on held-out test sets have varying results on these capabilities.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="macphail-etal-2024-evaluating">
<titleInfo>
<title>Evaluating the Robustness of Adverse Drug Event Classification Models using Templates</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dorothea</namePart>
<namePart type="family">MacPhail</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Harbecke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lisa</namePart>
<namePart type="family">Raithel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Möller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Workshop on Biomedical Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Miwa</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">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>An adverse drug effect (ADE) is any harmful event resulting from medical drug treatment. Despite their importance, ADEs are often under-reported in official channels. Some research has therefore turned to detecting discussions of ADEs in social media. Impressive results have been achieved in various attempts to detect ADEs. In a high-stakes domain such as medicine, however, an in-depth evaluation of a model’s abilities is crucial. We address the issue of thorough performance evaluation in detecting ADEs with hand-crafted templates for four capabilities, temporal order, negation, sentiment and beneficial effect. We find that models with similar performance on held-out test sets have varying results on these capabilities.</abstract>
<identifier type="citekey">macphail-etal-2024-evaluating</identifier>
<identifier type="doi">10.18653/v1/2024.bionlp-1.3</identifier>
<location>
<url>https://aclanthology.org/2024.bionlp-1.3</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>25</start>
<end>38</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating the Robustness of Adverse Drug Event Classification Models using Templates
%A MacPhail, Dorothea
%A Harbecke, David
%A Raithel, Lisa
%A Möller, Sebastian
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Miwa, Makoto
%Y Roberts, Kirk
%Y Tsujii, Junichi
%S Proceedings of the 23rd Workshop on Biomedical Natural Language Processing
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F macphail-etal-2024-evaluating
%X An adverse drug effect (ADE) is any harmful event resulting from medical drug treatment. Despite their importance, ADEs are often under-reported in official channels. Some research has therefore turned to detecting discussions of ADEs in social media. Impressive results have been achieved in various attempts to detect ADEs. In a high-stakes domain such as medicine, however, an in-depth evaluation of a model’s abilities is crucial. We address the issue of thorough performance evaluation in detecting ADEs with hand-crafted templates for four capabilities, temporal order, negation, sentiment and beneficial effect. We find that models with similar performance on held-out test sets have varying results on these capabilities.
%R 10.18653/v1/2024.bionlp-1.3
%U https://aclanthology.org/2024.bionlp-1.3
%U https://doi.org/10.18653/v1/2024.bionlp-1.3
%P 25-38
Markdown (Informal)
[Evaluating the Robustness of Adverse Drug Event Classification Models using Templates](https://aclanthology.org/2024.bionlp-1.3) (MacPhail et al., BioNLP-WS 2024)
ACL