@inproceedings{lamproudis-etal-2022-evaluating,
title = "Evaluating Pretraining Strategies for Clinical {BERT} Models",
author = "Lamproudis, Anastasios and
Henriksson, Aron and
Dalianis, Hercules",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.43",
pages = "410--416",
abstract = "Research suggests that using generic language models in specialized domains may be sub-optimal due to significant domain differences. As a result, various strategies for developing domain-specific language models have been proposed, including techniques for adapting an existing generic language model to the target domain, e.g. through various forms of vocabulary modifications and continued domain-adaptive pretraining with in-domain data. Here, an empirical investigation is carried out in which various strategies for adapting a generic language model to the clinical domain are compared to pretraining a pure clinical language model. Three clinical language models for Swedish, pretrained for up to ten epochs, are fine-tuned and evaluated on several downstream tasks in the clinical domain. A comparison of the language models{'} downstream performance over the training epochs is conducted. The results show that the domain-specific language models outperform a general-domain language model; however, there is little difference in performance of the various clinical language models. However, compared to pretraining a pure clinical language model with only in-domain data, leveraging and adapting an existing general-domain language model requires fewer epochs of pretraining with in-domain data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lamproudis-etal-2022-evaluating">
<titleInfo>
<title>Evaluating Pretraining Strategies for Clinical BERT Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anastasios</namePart>
<namePart type="family">Lamproudis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aron</namePart>
<namePart type="family">Henriksson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hercules</namePart>
<namePart type="family">Dalianis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Research suggests that using generic language models in specialized domains may be sub-optimal due to significant domain differences. As a result, various strategies for developing domain-specific language models have been proposed, including techniques for adapting an existing generic language model to the target domain, e.g. through various forms of vocabulary modifications and continued domain-adaptive pretraining with in-domain data. Here, an empirical investigation is carried out in which various strategies for adapting a generic language model to the clinical domain are compared to pretraining a pure clinical language model. Three clinical language models for Swedish, pretrained for up to ten epochs, are fine-tuned and evaluated on several downstream tasks in the clinical domain. A comparison of the language models’ downstream performance over the training epochs is conducted. The results show that the domain-specific language models outperform a general-domain language model; however, there is little difference in performance of the various clinical language models. However, compared to pretraining a pure clinical language model with only in-domain data, leveraging and adapting an existing general-domain language model requires fewer epochs of pretraining with in-domain data.</abstract>
<identifier type="citekey">lamproudis-etal-2022-evaluating</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.43</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>410</start>
<end>416</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Evaluating Pretraining Strategies for Clinical BERT Models
%A Lamproudis, Anastasios
%A Henriksson, Aron
%A Dalianis, Hercules
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F lamproudis-etal-2022-evaluating
%X Research suggests that using generic language models in specialized domains may be sub-optimal due to significant domain differences. As a result, various strategies for developing domain-specific language models have been proposed, including techniques for adapting an existing generic language model to the target domain, e.g. through various forms of vocabulary modifications and continued domain-adaptive pretraining with in-domain data. Here, an empirical investigation is carried out in which various strategies for adapting a generic language model to the clinical domain are compared to pretraining a pure clinical language model. Three clinical language models for Swedish, pretrained for up to ten epochs, are fine-tuned and evaluated on several downstream tasks in the clinical domain. A comparison of the language models’ downstream performance over the training epochs is conducted. The results show that the domain-specific language models outperform a general-domain language model; however, there is little difference in performance of the various clinical language models. However, compared to pretraining a pure clinical language model with only in-domain data, leveraging and adapting an existing general-domain language model requires fewer epochs of pretraining with in-domain data.
%U https://aclanthology.org/2022.lrec-1.43
%P 410-416
Markdown (Informal)
[Evaluating Pretraining Strategies for Clinical BERT Models](https://aclanthology.org/2022.lrec-1.43) (Lamproudis et al., LREC 2022)
ACL