@inproceedings{suresh-etal-2023-intermediate,
title = "Intermediate Domain Finetuning for Weakly Supervised Domain-adaptive Clinical {NER}",
author = "Suresh, Shilpa and
Tavabi, Nazgol and
Golchin, Shahriar and
Gilreath, Leah and
Garcia-Andujar, Rafael and
Kim, Alexander and
Murray, Joseph and
Bacevich, Blake and
Kiapour, Ata",
editor = "Demner-fushman, Dina and
Ananiadou, Sophia and
Cohen, Kevin",
booktitle = "The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.bionlp-1.29",
doi = "10.18653/v1/2023.bionlp-1.29",
pages = "320--325",
abstract = "Accurate human-annotated data for real-worlduse cases can be scarce and expensive to obtain. In the clinical domain, obtaining such data is evenmore difficult due to privacy concerns which notonly restrict open access to quality data but also require that the annotation be done by domain experts. In this paper, we propose a novel framework - InterDAPT - that leverages Intermediate Domain Finetuning to allow language models to adapt to narrow domains with small, noisy datasets. By making use of peripherally-related, unlabeled datasets,this framework circumvents domain-specific datascarcity issues. Our results show that this weaklysupervised framework provides performance improvements in downstream clinical named entityrecognition tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="suresh-etal-2023-intermediate">
<titleInfo>
<title>Intermediate Domain Finetuning for Weakly Supervised Domain-adaptive Clinical NER</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shilpa</namePart>
<namePart type="family">Suresh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nazgol</namePart>
<namePart type="family">Tavabi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shahriar</namePart>
<namePart type="family">Golchin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leah</namePart>
<namePart type="family">Gilreath</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="family">Garcia-Andujar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Murray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Blake</namePart>
<namePart type="family">Bacevich</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ata</namePart>
<namePart type="family">Kiapour</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks</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">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Accurate human-annotated data for real-worlduse cases can be scarce and expensive to obtain. In the clinical domain, obtaining such data is evenmore difficult due to privacy concerns which notonly restrict open access to quality data but also require that the annotation be done by domain experts. In this paper, we propose a novel framework - InterDAPT - that leverages Intermediate Domain Finetuning to allow language models to adapt to narrow domains with small, noisy datasets. By making use of peripherally-related, unlabeled datasets,this framework circumvents domain-specific datascarcity issues. Our results show that this weaklysupervised framework provides performance improvements in downstream clinical named entityrecognition tasks.</abstract>
<identifier type="citekey">suresh-etal-2023-intermediate</identifier>
<identifier type="doi">10.18653/v1/2023.bionlp-1.29</identifier>
<location>
<url>https://aclanthology.org/2023.bionlp-1.29</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>320</start>
<end>325</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Intermediate Domain Finetuning for Weakly Supervised Domain-adaptive Clinical NER
%A Suresh, Shilpa
%A Tavabi, Nazgol
%A Golchin, Shahriar
%A Gilreath, Leah
%A Garcia-Andujar, Rafael
%A Kim, Alexander
%A Murray, Joseph
%A Bacevich, Blake
%A Kiapour, Ata
%Y Demner-fushman, Dina
%Y Ananiadou, Sophia
%Y Cohen, Kevin
%S The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F suresh-etal-2023-intermediate
%X Accurate human-annotated data for real-worlduse cases can be scarce and expensive to obtain. In the clinical domain, obtaining such data is evenmore difficult due to privacy concerns which notonly restrict open access to quality data but also require that the annotation be done by domain experts. In this paper, we propose a novel framework - InterDAPT - that leverages Intermediate Domain Finetuning to allow language models to adapt to narrow domains with small, noisy datasets. By making use of peripherally-related, unlabeled datasets,this framework circumvents domain-specific datascarcity issues. Our results show that this weaklysupervised framework provides performance improvements in downstream clinical named entityrecognition tasks.
%R 10.18653/v1/2023.bionlp-1.29
%U https://aclanthology.org/2023.bionlp-1.29
%U https://doi.org/10.18653/v1/2023.bionlp-1.29
%P 320-325
Markdown (Informal)
[Intermediate Domain Finetuning for Weakly Supervised Domain-adaptive Clinical NER](https://aclanthology.org/2023.bionlp-1.29) (Suresh et al., BioNLP 2023)
ACL
- Shilpa Suresh, Nazgol Tavabi, Shahriar Golchin, Leah Gilreath, Rafael Garcia-Andujar, Alexander Kim, Joseph Murray, Blake Bacevich, and Ata Kiapour. 2023. Intermediate Domain Finetuning for Weakly Supervised Domain-adaptive Clinical NER. In The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks, pages 320–325, Toronto, Canada. Association for Computational Linguistics.