@inproceedings{mobasher-etal-2023-welt,
title = "{W}e{LT}: Improving Biomedical Fine-tuned Pre-trained Language Models with Cost-sensitive Learning",
author = {Mobasher, Ghadeer and
M{\"u}ller, Wolfgang and
Krebs, Olga and
Gertz, Michael},
editor = "Demner-fushman, Dina and
Ananiadou, Sophia and
Cohen, Kevin",
booktitle = "The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.bionlp-1.40",
doi = "10.18653/v1/2023.bionlp-1.40",
pages = "427--438",
abstract = "Fine-tuning biomedical pre-trained language models (BioPLMs) such as BioBERT has become a common practice dominating leaderboards across various natural language processing tasks. Despite their success and wide adoption, prevailing fine-tuning approaches for named entity recognition (NER) naively train BioPLMs on targeted datasets without considering class distributions. This is problematic especially when dealing with imbalanced biomedical gold-standard datasets for NER in which most biomedical entities are underrepresented. In this paper, we address the class imbalance problem and propose WeLT, a cost-sensitive fine-tuning approach based on new re-scaled class weights for the task of biomedical NER. We evaluate WeLT{'}s fine-tuning performance on mixed-domain and domain-specific BioPLMs using eight biomedical gold-standard datasets. We compare our approach against vanilla fine-tuning and three other existing re-weighting schemes. Our results show the positive impact of handling the class imbalance problem. WeLT outperforms all the vanilla fine-tuned models. Furthermore, our method demonstrates advantages over other existing weighting schemes in most experiments.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mobasher-etal-2023-welt">
<titleInfo>
<title>WeLT: Improving Biomedical Fine-tuned Pre-trained Language Models with Cost-sensitive Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ghadeer</namePart>
<namePart type="family">Mobasher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wolfgang</namePart>
<namePart type="family">Müller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Olga</namePart>
<namePart type="family">Krebs</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Gertz</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>The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks</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">Kevin</namePart>
<namePart type="family">Cohen</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>Fine-tuning biomedical pre-trained language models (BioPLMs) such as BioBERT has become a common practice dominating leaderboards across various natural language processing tasks. Despite their success and wide adoption, prevailing fine-tuning approaches for named entity recognition (NER) naively train BioPLMs on targeted datasets without considering class distributions. This is problematic especially when dealing with imbalanced biomedical gold-standard datasets for NER in which most biomedical entities are underrepresented. In this paper, we address the class imbalance problem and propose WeLT, a cost-sensitive fine-tuning approach based on new re-scaled class weights for the task of biomedical NER. We evaluate WeLT’s fine-tuning performance on mixed-domain and domain-specific BioPLMs using eight biomedical gold-standard datasets. We compare our approach against vanilla fine-tuning and three other existing re-weighting schemes. Our results show the positive impact of handling the class imbalance problem. WeLT outperforms all the vanilla fine-tuned models. Furthermore, our method demonstrates advantages over other existing weighting schemes in most experiments.</abstract>
<identifier type="citekey">mobasher-etal-2023-welt</identifier>
<identifier type="doi">10.18653/v1/2023.bionlp-1.40</identifier>
<location>
<url>https://aclanthology.org/2023.bionlp-1.40</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>427</start>
<end>438</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T WeLT: Improving Biomedical Fine-tuned Pre-trained Language Models with Cost-sensitive Learning
%A Mobasher, Ghadeer
%A Müller, Wolfgang
%A Krebs, Olga
%A Gertz, Michael
%Y Demner-fushman, Dina
%Y Ananiadou, Sophia
%Y Cohen, Kevin
%S The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F mobasher-etal-2023-welt
%X Fine-tuning biomedical pre-trained language models (BioPLMs) such as BioBERT has become a common practice dominating leaderboards across various natural language processing tasks. Despite their success and wide adoption, prevailing fine-tuning approaches for named entity recognition (NER) naively train BioPLMs on targeted datasets without considering class distributions. This is problematic especially when dealing with imbalanced biomedical gold-standard datasets for NER in which most biomedical entities are underrepresented. In this paper, we address the class imbalance problem and propose WeLT, a cost-sensitive fine-tuning approach based on new re-scaled class weights for the task of biomedical NER. We evaluate WeLT’s fine-tuning performance on mixed-domain and domain-specific BioPLMs using eight biomedical gold-standard datasets. We compare our approach against vanilla fine-tuning and three other existing re-weighting schemes. Our results show the positive impact of handling the class imbalance problem. WeLT outperforms all the vanilla fine-tuned models. Furthermore, our method demonstrates advantages over other existing weighting schemes in most experiments.
%R 10.18653/v1/2023.bionlp-1.40
%U https://aclanthology.org/2023.bionlp-1.40
%U https://doi.org/10.18653/v1/2023.bionlp-1.40
%P 427-438
Markdown (Informal)
[WeLT: Improving Biomedical Fine-tuned Pre-trained Language Models with Cost-sensitive Learning](https://aclanthology.org/2023.bionlp-1.40) (Mobasher et al., BioNLP 2023)
ACL