@inproceedings{lin-etal-2021-entitybert,
title = "{E}ntity{BERT}: Entity-centric Masking Strategy for Model Pretraining for the Clinical Domain",
author = "Lin, Chen and
Miller, Timothy and
Dligach, Dmitriy and
Bethard, Steven and
Savova, Guergana",
editor = "Demner-Fushman, Dina and
Cohen, Kevin Bretonnel and
Ananiadou, Sophia and
Tsujii, Junichi",
booktitle = "Proceedings of the 20th Workshop on Biomedical Language Processing",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.bionlp-1.21",
doi = "10.18653/v1/2021.bionlp-1.21",
pages = "191--201",
abstract = "Transformer-based neural language models have led to breakthroughs for a variety of natural language processing (NLP) tasks. However, most models are pretrained on general domain data. We propose a methodology to produce a model focused on the clinical domain: continued pretraining of a model with a broad representation of biomedical terminology (PubMedBERT) on a clinical corpus along with a novel entity-centric masking strategy to infuse domain knowledge in the learning process. We show that such a model achieves superior results on clinical extraction tasks by comparing our entity-centric masking strategy with classic random masking on three clinical NLP tasks: cross-domain negation detection, document time relation (DocTimeRel) classification, and temporal relation extraction. We also evaluate our models on the PubMedQA dataset to measure the models{'} performance on a non-entity-centric task in the biomedical domain. The language addressed in this work is English.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2021-entitybert">
<titleInfo>
<title>EntityBERT: Entity-centric Masking Strategy for Model Pretraining for the Clinical Domain</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Timothy</namePart>
<namePart type="family">Miller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dmitriy</namePart>
<namePart type="family">Dligach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guergana</namePart>
<namePart type="family">Savova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Workshop on Biomedical Language Processing</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">Kevin</namePart>
<namePart type="given">Bretonnel</namePart>
<namePart type="family">Cohen</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">Junichi</namePart>
<namePart type="family">Tsujii</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>Transformer-based neural language models have led to breakthroughs for a variety of natural language processing (NLP) tasks. However, most models are pretrained on general domain data. We propose a methodology to produce a model focused on the clinical domain: continued pretraining of a model with a broad representation of biomedical terminology (PubMedBERT) on a clinical corpus along with a novel entity-centric masking strategy to infuse domain knowledge in the learning process. We show that such a model achieves superior results on clinical extraction tasks by comparing our entity-centric masking strategy with classic random masking on three clinical NLP tasks: cross-domain negation detection, document time relation (DocTimeRel) classification, and temporal relation extraction. We also evaluate our models on the PubMedQA dataset to measure the models’ performance on a non-entity-centric task in the biomedical domain. The language addressed in this work is English.</abstract>
<identifier type="citekey">lin-etal-2021-entitybert</identifier>
<identifier type="doi">10.18653/v1/2021.bionlp-1.21</identifier>
<location>
<url>https://aclanthology.org/2021.bionlp-1.21</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>191</start>
<end>201</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EntityBERT: Entity-centric Masking Strategy for Model Pretraining for the Clinical Domain
%A Lin, Chen
%A Miller, Timothy
%A Dligach, Dmitriy
%A Bethard, Steven
%A Savova, Guergana
%Y Demner-Fushman, Dina
%Y Cohen, Kevin Bretonnel
%Y Ananiadou, Sophia
%Y Tsujii, Junichi
%S Proceedings of the 20th Workshop on Biomedical Language Processing
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F lin-etal-2021-entitybert
%X Transformer-based neural language models have led to breakthroughs for a variety of natural language processing (NLP) tasks. However, most models are pretrained on general domain data. We propose a methodology to produce a model focused on the clinical domain: continued pretraining of a model with a broad representation of biomedical terminology (PubMedBERT) on a clinical corpus along with a novel entity-centric masking strategy to infuse domain knowledge in the learning process. We show that such a model achieves superior results on clinical extraction tasks by comparing our entity-centric masking strategy with classic random masking on three clinical NLP tasks: cross-domain negation detection, document time relation (DocTimeRel) classification, and temporal relation extraction. We also evaluate our models on the PubMedQA dataset to measure the models’ performance on a non-entity-centric task in the biomedical domain. The language addressed in this work is English.
%R 10.18653/v1/2021.bionlp-1.21
%U https://aclanthology.org/2021.bionlp-1.21
%U https://doi.org/10.18653/v1/2021.bionlp-1.21
%P 191-201
Markdown (Informal)
[EntityBERT: Entity-centric Masking Strategy for Model Pretraining for the Clinical Domain](https://aclanthology.org/2021.bionlp-1.21) (Lin et al., BioNLP 2021)
ACL