@inproceedings{ghosh-etal-2024-healthalignsumm,
title = "{H}ealth{A}lign{S}umm : Utilizing Alignment for Multimodal Summarization of Code-Mixed Healthcare Dialogues",
author = "Ghosh, Akash and
Acharya, Arkadeep and
Saha, Sriparna and
Pandey, Gaurav and
Raghu, Dinesh and
Sinha, Setu",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.675",
pages = "11546--11560",
abstract = "As generative AI progresses, collaboration be-tween doctors and AI scientists is leading to thedevelopment of personalized models to stream-line healthcare tasks and improve productivity.Summarizing doctor-patient dialogues has be-come important, helping doctors understandconversations faster and improving patient care.While previous research has mostly focused ontext data, incorporating visual cues from pa-tient interactions allows doctors to gain deeperinsights into medical conditions. Most of thisresearch has centered on English datasets, butreal-world conversations often mix languagesfor better communication. To address the lackof resources for multimodal summarization ofcode-mixed dialogues in healthcare, we devel-oped the MCDH dataset. Additionally, we cre-ated HealthAlignSumm, a new model that in-tegrates visual components with the BART ar-chitecture. This represents a key advancementin multimodal fusion, applied within both theencoder and decoder of the BART model. Ourwork is the first to use alignment techniques,including state-of-the-art algorithms like DirectPreference Optimization, on encoder-decodermodels with synthetic datasets for multimodalsummarization. Through extensive experi-ments, we demonstrated the superior perfor-mance of HealthAlignSumm across severalmetrics validated by both automated assess-ments and human evaluations. The datasetMCDH and our proposed model HealthAlign-Summ will be available in this GitHub accounthttps://github.com/AkashGhosh/HealthAlignSumm-Utilizing-Alignment-for-Multimodal-Summarization-of-Code-Mixed-Healthcare-DialoguesDisclaimer: This work involves medical im-agery based on the subject matter of the topic.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ghosh-etal-2024-healthalignsumm">
<titleInfo>
<title>HealthAlignSumm : Utilizing Alignment for Multimodal Summarization of Code-Mixed Healthcare Dialogues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Akash</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arkadeep</namePart>
<namePart type="family">Acharya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sriparna</namePart>
<namePart type="family">Saha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gaurav</namePart>
<namePart type="family">Pandey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dinesh</namePart>
<namePart type="family">Raghu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Setu</namePart>
<namePart type="family">Sinha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As generative AI progresses, collaboration be-tween doctors and AI scientists is leading to thedevelopment of personalized models to stream-line healthcare tasks and improve productivity.Summarizing doctor-patient dialogues has be-come important, helping doctors understandconversations faster and improving patient care.While previous research has mostly focused ontext data, incorporating visual cues from pa-tient interactions allows doctors to gain deeperinsights into medical conditions. Most of thisresearch has centered on English datasets, butreal-world conversations often mix languagesfor better communication. To address the lackof resources for multimodal summarization ofcode-mixed dialogues in healthcare, we devel-oped the MCDH dataset. Additionally, we cre-ated HealthAlignSumm, a new model that in-tegrates visual components with the BART ar-chitecture. This represents a key advancementin multimodal fusion, applied within both theencoder and decoder of the BART model. Ourwork is the first to use alignment techniques,including state-of-the-art algorithms like DirectPreference Optimization, on encoder-decodermodels with synthetic datasets for multimodalsummarization. Through extensive experi-ments, we demonstrated the superior perfor-mance of HealthAlignSumm across severalmetrics validated by both automated assess-ments and human evaluations. The datasetMCDH and our proposed model HealthAlign-Summ will be available in this GitHub accounthttps://github.com/AkashGhosh/HealthAlignSumm-Utilizing-Alignment-for-Multimodal-Summarization-of-Code-Mixed-Healthcare-DialoguesDisclaimer: This work involves medical im-agery based on the subject matter of the topic.</abstract>
<identifier type="citekey">ghosh-etal-2024-healthalignsumm</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.675</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>11546</start>
<end>11560</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T HealthAlignSumm : Utilizing Alignment for Multimodal Summarization of Code-Mixed Healthcare Dialogues
%A Ghosh, Akash
%A Acharya, Arkadeep
%A Saha, Sriparna
%A Pandey, Gaurav
%A Raghu, Dinesh
%A Sinha, Setu
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F ghosh-etal-2024-healthalignsumm
%X As generative AI progresses, collaboration be-tween doctors and AI scientists is leading to thedevelopment of personalized models to stream-line healthcare tasks and improve productivity.Summarizing doctor-patient dialogues has be-come important, helping doctors understandconversations faster and improving patient care.While previous research has mostly focused ontext data, incorporating visual cues from pa-tient interactions allows doctors to gain deeperinsights into medical conditions. Most of thisresearch has centered on English datasets, butreal-world conversations often mix languagesfor better communication. To address the lackof resources for multimodal summarization ofcode-mixed dialogues in healthcare, we devel-oped the MCDH dataset. Additionally, we cre-ated HealthAlignSumm, a new model that in-tegrates visual components with the BART ar-chitecture. This represents a key advancementin multimodal fusion, applied within both theencoder and decoder of the BART model. Ourwork is the first to use alignment techniques,including state-of-the-art algorithms like DirectPreference Optimization, on encoder-decodermodels with synthetic datasets for multimodalsummarization. Through extensive experi-ments, we demonstrated the superior perfor-mance of HealthAlignSumm across severalmetrics validated by both automated assess-ments and human evaluations. The datasetMCDH and our proposed model HealthAlign-Summ will be available in this GitHub accounthttps://github.com/AkashGhosh/HealthAlignSumm-Utilizing-Alignment-for-Multimodal-Summarization-of-Code-Mixed-Healthcare-DialoguesDisclaimer: This work involves medical im-agery based on the subject matter of the topic.
%U https://aclanthology.org/2024.findings-emnlp.675
%P 11546-11560
Markdown (Informal)
[HealthAlignSumm : Utilizing Alignment for Multimodal Summarization of Code-Mixed Healthcare Dialogues](https://aclanthology.org/2024.findings-emnlp.675) (Ghosh et al., Findings 2024)
ACL