@inproceedings{lewis-etal-2020-pretrained,
title = "Pretrained Language Models for Biomedical and Clinical Tasks: Understanding and Extending the State-of-the-Art",
author = "Lewis, Patrick and
Ott, Myle and
Du, Jingfei and
Stoyanov, Veselin",
editor = "Rumshisky, Anna and
Roberts, Kirk and
Bethard, Steven and
Naumann, Tristan",
booktitle = "Proceedings of the 3rd Clinical Natural Language Processing Workshop",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.clinicalnlp-1.17",
doi = "10.18653/v1/2020.clinicalnlp-1.17",
pages = "146--157",
abstract = "A large array of pretrained models are available to the biomedical NLP (BioNLP) community. Finding the best model for a particular task can be difficult and time-consuming. For many applications in the biomedical and clinical domains, it is crucial that models can be built quickly and are highly accurate. We present a large-scale study across 18 established biomedical and clinical NLP tasks to determine which of several popular open-source biomedical and clinical NLP models work well in different settings. Furthermore, we apply recent advances in pretraining to train new biomedical language models, and carefully investigate the effect of various design choices on downstream performance. Our best models perform well in all of our benchmarks, and set new State-of-the-Art in 9 tasks. We release these models in the hope that they can help the community to speed up and increase the accuracy of BioNLP and text mining applications.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lewis-etal-2020-pretrained">
<titleInfo>
<title>Pretrained Language Models for Biomedical and Clinical Tasks: Understanding and Extending the State-of-the-Art</title>
</titleInfo>
<name type="personal">
<namePart type="given">Patrick</namePart>
<namePart type="family">Lewis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Myle</namePart>
<namePart type="family">Ott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jingfei</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veselin</namePart>
<namePart type="family">Stoyanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 3rd Clinical Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</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">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Naumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>A large array of pretrained models are available to the biomedical NLP (BioNLP) community. Finding the best model for a particular task can be difficult and time-consuming. For many applications in the biomedical and clinical domains, it is crucial that models can be built quickly and are highly accurate. We present a large-scale study across 18 established biomedical and clinical NLP tasks to determine which of several popular open-source biomedical and clinical NLP models work well in different settings. Furthermore, we apply recent advances in pretraining to train new biomedical language models, and carefully investigate the effect of various design choices on downstream performance. Our best models perform well in all of our benchmarks, and set new State-of-the-Art in 9 tasks. We release these models in the hope that they can help the community to speed up and increase the accuracy of BioNLP and text mining applications.</abstract>
<identifier type="citekey">lewis-etal-2020-pretrained</identifier>
<identifier type="doi">10.18653/v1/2020.clinicalnlp-1.17</identifier>
<location>
<url>https://aclanthology.org/2020.clinicalnlp-1.17</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>146</start>
<end>157</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Pretrained Language Models for Biomedical and Clinical Tasks: Understanding and Extending the State-of-the-Art
%A Lewis, Patrick
%A Ott, Myle
%A Du, Jingfei
%A Stoyanov, Veselin
%Y Rumshisky, Anna
%Y Roberts, Kirk
%Y Bethard, Steven
%Y Naumann, Tristan
%S Proceedings of the 3rd Clinical Natural Language Processing Workshop
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F lewis-etal-2020-pretrained
%X A large array of pretrained models are available to the biomedical NLP (BioNLP) community. Finding the best model for a particular task can be difficult and time-consuming. For many applications in the biomedical and clinical domains, it is crucial that models can be built quickly and are highly accurate. We present a large-scale study across 18 established biomedical and clinical NLP tasks to determine which of several popular open-source biomedical and clinical NLP models work well in different settings. Furthermore, we apply recent advances in pretraining to train new biomedical language models, and carefully investigate the effect of various design choices on downstream performance. Our best models perform well in all of our benchmarks, and set new State-of-the-Art in 9 tasks. We release these models in the hope that they can help the community to speed up and increase the accuracy of BioNLP and text mining applications.
%R 10.18653/v1/2020.clinicalnlp-1.17
%U https://aclanthology.org/2020.clinicalnlp-1.17
%U https://doi.org/10.18653/v1/2020.clinicalnlp-1.17
%P 146-157
Markdown (Informal)
[Pretrained Language Models for Biomedical and Clinical Tasks: Understanding and Extending the State-of-the-Art](https://aclanthology.org/2020.clinicalnlp-1.17) (Lewis et al., ClinicalNLP 2020)
ACL