@inproceedings{sanchez-carmona-etal-2024-multilevel,
title = "A Multilevel Analysis of {P}ub{M}ed-only {BERT}-based Biomedical Models",
author = "Sanchez Carmona, Vicente and
Jiang, Shanshan and
Dong, Bin",
editor = "Naumann, Tristan and
Ben Abacha, Asma and
Bethard, Steven and
Roberts, Kirk and
Bitterman, Danielle",
booktitle = "Proceedings of the 6th Clinical Natural Language Processing Workshop",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.clinicalnlp-1.10",
pages = "105--110",
abstract = "Biomedical NLP models play a big role in the automatic extraction of information from biomedical documents, such as COVID research papers. Three landmark models have led the way in this area: BioBERT, MSR BiomedBERT, and BioLinkBERT. However, their shallow evaluation {--}a single mean score{--} forbid us to better understand how the contributions proposed in each model advance the Biomedical NLP field. We show through a Multilevel Analysis how we can assess these contributions. Our analyses across 5000 fine-tuned models show that, actually, BiomedBERT{'}s true effect is bigger than BioLinkBERT{'}s effect, and the success of BioLinkBERT does not seem to be due to its contribution {--}the Link function{--} but due to an unknown factor.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sanchez-carmona-etal-2024-multilevel">
<titleInfo>
<title>A Multilevel Analysis of PubMed-only BERT-based Biomedical Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Vicente</namePart>
<namePart type="family">Sanchez Carmona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shanshan</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 6th 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">Danielle</namePart>
<namePart type="family">Bitterman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Biomedical NLP models play a big role in the automatic extraction of information from biomedical documents, such as COVID research papers. Three landmark models have led the way in this area: BioBERT, MSR BiomedBERT, and BioLinkBERT. However, their shallow evaluation –a single mean score– forbid us to better understand how the contributions proposed in each model advance the Biomedical NLP field. We show through a Multilevel Analysis how we can assess these contributions. Our analyses across 5000 fine-tuned models show that, actually, BiomedBERT’s true effect is bigger than BioLinkBERT’s effect, and the success of BioLinkBERT does not seem to be due to its contribution –the Link function– but due to an unknown factor.</abstract>
<identifier type="citekey">sanchez-carmona-etal-2024-multilevel</identifier>
<location>
<url>https://aclanthology.org/2024.clinicalnlp-1.10</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>105</start>
<end>110</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Multilevel Analysis of PubMed-only BERT-based Biomedical Models
%A Sanchez Carmona, Vicente
%A Jiang, Shanshan
%A Dong, Bin
%Y Naumann, Tristan
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Roberts, Kirk
%Y Bitterman, Danielle
%S Proceedings of the 6th Clinical Natural Language Processing Workshop
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F sanchez-carmona-etal-2024-multilevel
%X Biomedical NLP models play a big role in the automatic extraction of information from biomedical documents, such as COVID research papers. Three landmark models have led the way in this area: BioBERT, MSR BiomedBERT, and BioLinkBERT. However, their shallow evaluation –a single mean score– forbid us to better understand how the contributions proposed in each model advance the Biomedical NLP field. We show through a Multilevel Analysis how we can assess these contributions. Our analyses across 5000 fine-tuned models show that, actually, BiomedBERT’s true effect is bigger than BioLinkBERT’s effect, and the success of BioLinkBERT does not seem to be due to its contribution –the Link function– but due to an unknown factor.
%U https://aclanthology.org/2024.clinicalnlp-1.10
%P 105-110
Markdown (Informal)
[A Multilevel Analysis of PubMed-only BERT-based Biomedical Models](https://aclanthology.org/2024.clinicalnlp-1.10) (Sanchez Carmona et al., ClinicalNLP-WS 2024)
ACL