@inproceedings{tai-etal-2020-exbert,
title = "ex{BERT}: Extending Pre-trained Models with Domain-specific Vocabulary Under Constrained Training Resources",
author = "Tai, Wen and
Kung, H. T. and
Dong, Xin and
Comiter, Marcus and
Kuo, Chang-Fu",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.129",
doi = "10.18653/v1/2020.findings-emnlp.129",
pages = "1433--1439",
abstract = "We introduce exBERT, a training method to extend BERT pre-trained models from a general domain to a new pre-trained model for a specific domain with a new additive vocabulary under constrained training resources (i.e., constrained computation and data). exBERT uses a small extension module to learn to adapt an augmenting embedding for the new domain in the context of the original BERT{'}s embedding of a general vocabulary. The exBERT training method is novel in learning the new vocabulary and the extension module while keeping the weights of the original BERT model fixed, resulting in a substantial reduction in required training resources. We pre-train exBERT with biomedical articles from ClinicalKey and PubMed Central, and study its performance on biomedical downstream benchmark tasks using the MTL-Bioinformatics-2016 datasets. We demonstrate that exBERT consistently outperforms prior approaches when using limited corpus and pre-training computation resources.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tai-etal-2020-exbert">
<titleInfo>
<title>exBERT: Extending Pre-trained Models with Domain-specific Vocabulary Under Constrained Training Resources</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wen</namePart>
<namePart type="family">Tai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">H</namePart>
<namePart type="given">T</namePart>
<namePart type="family">Kung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcus</namePart>
<namePart type="family">Comiter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chang-Fu</namePart>
<namePart type="family">Kuo</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>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</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>We introduce exBERT, a training method to extend BERT pre-trained models from a general domain to a new pre-trained model for a specific domain with a new additive vocabulary under constrained training resources (i.e., constrained computation and data). exBERT uses a small extension module to learn to adapt an augmenting embedding for the new domain in the context of the original BERT’s embedding of a general vocabulary. The exBERT training method is novel in learning the new vocabulary and the extension module while keeping the weights of the original BERT model fixed, resulting in a substantial reduction in required training resources. We pre-train exBERT with biomedical articles from ClinicalKey and PubMed Central, and study its performance on biomedical downstream benchmark tasks using the MTL-Bioinformatics-2016 datasets. We demonstrate that exBERT consistently outperforms prior approaches when using limited corpus and pre-training computation resources.</abstract>
<identifier type="citekey">tai-etal-2020-exbert</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.129</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.129</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>1433</start>
<end>1439</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T exBERT: Extending Pre-trained Models with Domain-specific Vocabulary Under Constrained Training Resources
%A Tai, Wen
%A Kung, H. T.
%A Dong, Xin
%A Comiter, Marcus
%A Kuo, Chang-Fu
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F tai-etal-2020-exbert
%X We introduce exBERT, a training method to extend BERT pre-trained models from a general domain to a new pre-trained model for a specific domain with a new additive vocabulary under constrained training resources (i.e., constrained computation and data). exBERT uses a small extension module to learn to adapt an augmenting embedding for the new domain in the context of the original BERT’s embedding of a general vocabulary. The exBERT training method is novel in learning the new vocabulary and the extension module while keeping the weights of the original BERT model fixed, resulting in a substantial reduction in required training resources. We pre-train exBERT with biomedical articles from ClinicalKey and PubMed Central, and study its performance on biomedical downstream benchmark tasks using the MTL-Bioinformatics-2016 datasets. We demonstrate that exBERT consistently outperforms prior approaches when using limited corpus and pre-training computation resources.
%R 10.18653/v1/2020.findings-emnlp.129
%U https://aclanthology.org/2020.findings-emnlp.129
%U https://doi.org/10.18653/v1/2020.findings-emnlp.129
%P 1433-1439
Markdown (Informal)
[exBERT: Extending Pre-trained Models with Domain-specific Vocabulary Under Constrained Training Resources](https://aclanthology.org/2020.findings-emnlp.129) (Tai et al., Findings 2020)
ACL