@inproceedings{ghosh-etal-2023-radling,
title = "{R}ad{L}ing: Towards Efficient Radiology Report Understanding",
author = "Ghosh, Rikhiya and
Farri, Oladimeji and
Karn, Sanjeev Kumar and
Danu, Manuela and
Vunikili, Ramya and
Micu, Larisa",
editor = "Sitaram, Sunayana and
Beigman Klebanov, Beata and
Williams, Jason D",
booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.acl-industry.61",
doi = "10.18653/v1/2023.acl-industry.61",
pages = "640--651",
abstract = "Most natural language tasks in the radiology domain use language models pre-trained on biomedical corpus. There are few pretrained language models trained specifically for radiology, and fewer still that have been trained in a low data setting and gone on to produce comparable results in fine-tuning tasks. We present RadLing, a continuously pretrained language model using ELECTRA-small architecture, trained using over 500K radiology reports that can compete with state-of-the-art results for fine tuning tasks in radiology domain. Our main contribution in this paper is knowledge-aware masking which is an taxonomic knowledge-assisted pre-training task that dynamically masks tokens to inject knowledge during pretraining. In addition, we also introduce an knowledge base-aided vocabulary extension to adapt the general tokenization vocabulary to radiology domain.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghosh-etal-2023-radling">
<titleInfo>
<title>RadLing: Towards Efficient Radiology Report Understanding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Rikhiya</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Oladimeji</namePart>
<namePart type="family">Farri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sanjeev</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Karn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manuela</namePart>
<namePart type="family">Danu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramya</namePart>
<namePart type="family">Vunikili</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Larisa</namePart>
<namePart type="family">Micu</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>Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sunayana</namePart>
<namePart type="family">Sitaram</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Beata</namePart>
<namePart type="family">Beigman Klebanov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="given">D</namePart>
<namePart type="family">Williams</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>Most natural language tasks in the radiology domain use language models pre-trained on biomedical corpus. There are few pretrained language models trained specifically for radiology, and fewer still that have been trained in a low data setting and gone on to produce comparable results in fine-tuning tasks. We present RadLing, a continuously pretrained language model using ELECTRA-small architecture, trained using over 500K radiology reports that can compete with state-of-the-art results for fine tuning tasks in radiology domain. Our main contribution in this paper is knowledge-aware masking which is an taxonomic knowledge-assisted pre-training task that dynamically masks tokens to inject knowledge during pretraining. In addition, we also introduce an knowledge base-aided vocabulary extension to adapt the general tokenization vocabulary to radiology domain.</abstract>
<identifier type="citekey">ghosh-etal-2023-radling</identifier>
<identifier type="doi">10.18653/v1/2023.acl-industry.61</identifier>
<location>
<url>https://aclanthology.org/2023.acl-industry.61</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>640</start>
<end>651</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RadLing: Towards Efficient Radiology Report Understanding
%A Ghosh, Rikhiya
%A Farri, Oladimeji
%A Karn, Sanjeev Kumar
%A Danu, Manuela
%A Vunikili, Ramya
%A Micu, Larisa
%Y Sitaram, Sunayana
%Y Beigman Klebanov, Beata
%Y Williams, Jason D.
%S Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F ghosh-etal-2023-radling
%X Most natural language tasks in the radiology domain use language models pre-trained on biomedical corpus. There are few pretrained language models trained specifically for radiology, and fewer still that have been trained in a low data setting and gone on to produce comparable results in fine-tuning tasks. We present RadLing, a continuously pretrained language model using ELECTRA-small architecture, trained using over 500K radiology reports that can compete with state-of-the-art results for fine tuning tasks in radiology domain. Our main contribution in this paper is knowledge-aware masking which is an taxonomic knowledge-assisted pre-training task that dynamically masks tokens to inject knowledge during pretraining. In addition, we also introduce an knowledge base-aided vocabulary extension to adapt the general tokenization vocabulary to radiology domain.
%R 10.18653/v1/2023.acl-industry.61
%U https://aclanthology.org/2023.acl-industry.61
%U https://doi.org/10.18653/v1/2023.acl-industry.61
%P 640-651
Markdown (Informal)
[RadLing: Towards Efficient Radiology Report Understanding](https://aclanthology.org/2023.acl-industry.61) (Ghosh et al., ACL 2023)
ACL
- Rikhiya Ghosh, Oladimeji Farri, Sanjeev Kumar Karn, Manuela Danu, Ramya Vunikili, and Larisa Micu. 2023. RadLing: Towards Efficient Radiology Report Understanding. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 5: Industry Track), pages 640–651, Toronto, Canada. Association for Computational Linguistics.