@inproceedings{gupta-etal-2024-towards,
title = "Towards Answering Health-related Questions from Medical Videos: Datasets and Approaches",
author = "Gupta, Deepak and
Attal, Kush and
Demner-Fushman, Dina",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1425",
pages = "16399--16411",
abstract = "The increase in the availability of online videos has transformed the way we access information and knowledge. A growing number of individuals now prefer instructional videos as they offer a series of step-by-step procedures to accomplish particular tasks. Instructional videos from the medical domain may provide the best possible visual answers to first aid, medical emergency, and medical education questions. This paper focuses on answering health-related questions asked by health consumers by providing visual answers from medical videos. The scarcity of large-scale datasets in the medical domain is a key challenge that hinders the development of applications that can help the public with their health-related questions. To address this issue, we first proposed a pipelined approach to create two large-scale datasets: HealthVidQA-CRF and HealthVidQA-Prompt. Leveraging the datasets, we developed monomodal and multimodal approaches that can effectively provide visual answers from medical videos to natural language questions. We conducted a comprehensive analysis of the results and outlined the findings, focusing on the impact of the created datasets on model training and the significance of visual features in enhancing the performance of the monomodal and multi-modal approaches for medical visual answer localization task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gupta-etal-2024-towards">
<titleInfo>
<title>Towards Answering Health-related Questions from Medical Videos: Datasets and Approaches</title>
</titleInfo>
<name type="personal">
<namePart type="given">Deepak</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kush</namePart>
<namePart type="family">Attal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The increase in the availability of online videos has transformed the way we access information and knowledge. A growing number of individuals now prefer instructional videos as they offer a series of step-by-step procedures to accomplish particular tasks. Instructional videos from the medical domain may provide the best possible visual answers to first aid, medical emergency, and medical education questions. This paper focuses on answering health-related questions asked by health consumers by providing visual answers from medical videos. The scarcity of large-scale datasets in the medical domain is a key challenge that hinders the development of applications that can help the public with their health-related questions. To address this issue, we first proposed a pipelined approach to create two large-scale datasets: HealthVidQA-CRF and HealthVidQA-Prompt. Leveraging the datasets, we developed monomodal and multimodal approaches that can effectively provide visual answers from medical videos to natural language questions. We conducted a comprehensive analysis of the results and outlined the findings, focusing on the impact of the created datasets on model training and the significance of visual features in enhancing the performance of the monomodal and multi-modal approaches for medical visual answer localization task.</abstract>
<identifier type="citekey">gupta-etal-2024-towards</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1425</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>16399</start>
<end>16411</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Answering Health-related Questions from Medical Videos: Datasets and Approaches
%A Gupta, Deepak
%A Attal, Kush
%A Demner-Fushman, Dina
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F gupta-etal-2024-towards
%X The increase in the availability of online videos has transformed the way we access information and knowledge. A growing number of individuals now prefer instructional videos as they offer a series of step-by-step procedures to accomplish particular tasks. Instructional videos from the medical domain may provide the best possible visual answers to first aid, medical emergency, and medical education questions. This paper focuses on answering health-related questions asked by health consumers by providing visual answers from medical videos. The scarcity of large-scale datasets in the medical domain is a key challenge that hinders the development of applications that can help the public with their health-related questions. To address this issue, we first proposed a pipelined approach to create two large-scale datasets: HealthVidQA-CRF and HealthVidQA-Prompt. Leveraging the datasets, we developed monomodal and multimodal approaches that can effectively provide visual answers from medical videos to natural language questions. We conducted a comprehensive analysis of the results and outlined the findings, focusing on the impact of the created datasets on model training and the significance of visual features in enhancing the performance of the monomodal and multi-modal approaches for medical visual answer localization task.
%U https://aclanthology.org/2024.lrec-main.1425
%P 16399-16411
Markdown (Informal)
[Towards Answering Health-related Questions from Medical Videos: Datasets and Approaches](https://aclanthology.org/2024.lrec-main.1425) (Gupta et al., LREC-COLING 2024)
ACL