@inproceedings{kim-etal-2023-ku,
title = "{KU}-{DMIS}-{MSRA} at {R}ad{S}um23: Pre-trained Vision-Language Model for Radiology Report Summarization",
author = "Kim, Gangwoo and
Kim, Hajung and
Ji, Lei and
Bae, Seongsu and
Kim, Chanhwi and
Sung, Mujeen and
Kim, Hyunjae and
Yan, Kun and
Chang, Eric and
Kang, Jaewoo",
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-1.59",
doi = "10.18653/v1/2023.bionlp-1.59",
pages = "567--573",
abstract = "In this paper, we introduce CheXOFA, a new pre-trained vision-language model (VLM) for the chest X-ray domain. Our model is initially pre-trained on various multimodal datasets within the general domain before being transferred to the chest X-ray domain. Following a prominent VLM, we unify various domain-specific tasks into a simple sequence-to-sequence schema. It enables the model to effectively learn the required knowledge and skills from limited resources in the domain. Demonstrating superior performance on the benchmark datasets provided by the BioNLP shared task (Delbrouck et al., 2023), our model benefits from its training across multiple tasks and domains. With subtle techniques including ensemble and factual calibration, our system achieves first place on the RadSum23 leaderboard for the hidden test set.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kim-etal-2023-ku">
<titleInfo>
<title>KU-DMIS-MSRA at RadSum23: Pre-trained Vision-Language Model for Radiology Report Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gangwoo</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hajung</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Ji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seongsu</namePart>
<namePart type="family">Bae</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chanhwi</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mujeen</namePart>
<namePart type="family">Sung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyunjae</namePart>
<namePart type="family">Kim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eric</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jaewoo</namePart>
<namePart type="family">Kang</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>In this paper, we introduce CheXOFA, a new pre-trained vision-language model (VLM) for the chest X-ray domain. Our model is initially pre-trained on various multimodal datasets within the general domain before being transferred to the chest X-ray domain. Following a prominent VLM, we unify various domain-specific tasks into a simple sequence-to-sequence schema. It enables the model to effectively learn the required knowledge and skills from limited resources in the domain. Demonstrating superior performance on the benchmark datasets provided by the BioNLP shared task (Delbrouck et al., 2023), our model benefits from its training across multiple tasks and domains. With subtle techniques including ensemble and factual calibration, our system achieves first place on the RadSum23 leaderboard for the hidden test set.</abstract>
<identifier type="citekey">kim-etal-2023-ku</identifier>
<identifier type="doi">10.18653/v1/2023.bionlp-1.59</identifier>
<location>
<url>https://aclanthology.org/2023.bionlp-1.59</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>567</start>
<end>573</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KU-DMIS-MSRA at RadSum23: Pre-trained Vision-Language Model for Radiology Report Summarization
%A Kim, Gangwoo
%A Kim, Hajung
%A Ji, Lei
%A Bae, Seongsu
%A Kim, Chanhwi
%A Sung, Mujeen
%A Kim, Hyunjae
%A Yan, Kun
%A Chang, Eric
%A Kang, Jaewoo
%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 kim-etal-2023-ku
%X In this paper, we introduce CheXOFA, a new pre-trained vision-language model (VLM) for the chest X-ray domain. Our model is initially pre-trained on various multimodal datasets within the general domain before being transferred to the chest X-ray domain. Following a prominent VLM, we unify various domain-specific tasks into a simple sequence-to-sequence schema. It enables the model to effectively learn the required knowledge and skills from limited resources in the domain. Demonstrating superior performance on the benchmark datasets provided by the BioNLP shared task (Delbrouck et al., 2023), our model benefits from its training across multiple tasks and domains. With subtle techniques including ensemble and factual calibration, our system achieves first place on the RadSum23 leaderboard for the hidden test set.
%R 10.18653/v1/2023.bionlp-1.59
%U https://aclanthology.org/2023.bionlp-1.59
%U https://doi.org/10.18653/v1/2023.bionlp-1.59
%P 567-573
Markdown (Informal)
[KU-DMIS-MSRA at RadSum23: Pre-trained Vision-Language Model for Radiology Report Summarization](https://aclanthology.org/2023.bionlp-1.59) (Kim et al., BioNLP 2023)
ACL
- Gangwoo Kim, Hajung Kim, Lei Ji, Seongsu Bae, Chanhwi Kim, Mujeen Sung, Hyunjae Kim, Kun Yan, Eric Chang, and Jaewoo Kang. 2023. KU-DMIS-MSRA at RadSum23: Pre-trained Vision-Language Model for Radiology Report Summarization. In The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks, pages 567–573, Toronto, Canada. Association for Computational Linguistics.