@inproceedings{koto-fang-2021-handling,
title = "Handling Variance of Pretrained Language Models in Grading Evidence in the Medical Literature",
author = "Koto, Fajri and
Fang, Biaoyan",
editor = "Rahimi, Afshin and
Lane, William and
Zuccon, Guido",
booktitle = "Proceedings of the 19th Annual Workshop of the Australasian Language Technology Association",
month = dec,
year = "2021",
address = "Online",
publisher = "Australasian Language Technology Association",
url = "https://aclanthology.org/2021.alta-1.26",
pages = "218--223",
abstract = "In this paper, we investigate the utility of modern pretrained language models for the evidence grading system in the medical literature based on the ALTA 2021 shared task. We benchmark 1) domain-specific models that are optimized for medical literature and 2) domain-generic models with rich latent discourse representation (i.e. ELECTRA, RoBERTa). Our empirical experiments reveal that these modern pretrained language models suffer from high variance, and the ensemble method can improve the model performance. We found that ELECTRA performs best with an accuracy of 53.6{\%} on the test set, outperforming domain-specific models.1",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="koto-fang-2021-handling">
<titleInfo>
<title>Handling Variance of Pretrained Language Models in Grading Evidence in the Medical Literature</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fajri</namePart>
<namePart type="family">Koto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Biaoyan</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 19th Annual Workshop of the Australasian Language Technology Association</title>
</titleInfo>
<name type="personal">
<namePart type="given">Afshin</namePart>
<namePart type="family">Rahimi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">William</namePart>
<namePart type="family">Lane</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guido</namePart>
<namePart type="family">Zuccon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Australasian Language Technology Association</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In this paper, we investigate the utility of modern pretrained language models for the evidence grading system in the medical literature based on the ALTA 2021 shared task. We benchmark 1) domain-specific models that are optimized for medical literature and 2) domain-generic models with rich latent discourse representation (i.e. ELECTRA, RoBERTa). Our empirical experiments reveal that these modern pretrained language models suffer from high variance, and the ensemble method can improve the model performance. We found that ELECTRA performs best with an accuracy of 53.6% on the test set, outperforming domain-specific models.1</abstract>
<identifier type="citekey">koto-fang-2021-handling</identifier>
<location>
<url>https://aclanthology.org/2021.alta-1.26</url>
</location>
<part>
<date>2021-12</date>
<extent unit="page">
<start>218</start>
<end>223</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Handling Variance of Pretrained Language Models in Grading Evidence in the Medical Literature
%A Koto, Fajri
%A Fang, Biaoyan
%Y Rahimi, Afshin
%Y Lane, William
%Y Zuccon, Guido
%S Proceedings of the 19th Annual Workshop of the Australasian Language Technology Association
%D 2021
%8 December
%I Australasian Language Technology Association
%C Online
%F koto-fang-2021-handling
%X In this paper, we investigate the utility of modern pretrained language models for the evidence grading system in the medical literature based on the ALTA 2021 shared task. We benchmark 1) domain-specific models that are optimized for medical literature and 2) domain-generic models with rich latent discourse representation (i.e. ELECTRA, RoBERTa). Our empirical experiments reveal that these modern pretrained language models suffer from high variance, and the ensemble method can improve the model performance. We found that ELECTRA performs best with an accuracy of 53.6% on the test set, outperforming domain-specific models.1
%U https://aclanthology.org/2021.alta-1.26
%P 218-223
Markdown (Informal)
[Handling Variance of Pretrained Language Models in Grading Evidence in the Medical Literature](https://aclanthology.org/2021.alta-1.26) (Koto & Fang, ALTA 2021)
ACL