@inproceedings{kumar-etal-2025-saha,
title = "{SAHA}: Samvad {AI} for Healthcare Assistance",
author = "Kumar, Aditya and
Nayak, Rakesh Kumar and
Naik, Janhavi and
Kumar, Ritesh and
Bhatia, Dhiraj and
Agarwal, Shreya",
editor = "Krishnamurthy, Parameswari and
Mujadia, Vandan and
Misra Sharma, Dipti and
Mary Thomas, Hannah",
booktitle = "NLP-AI4Health",
month = dec,
year = "2025",
address = "Mumbai, India",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.nlpai4health-main.8/",
pages = "80--85",
ISBN = "979-8-89176-315-9",
abstract = "This paper deals with the dual task of developing a medical question answering (QA) system and generating concise summaries of medical dialogue data across nine languages (English and eight Indian languages). The medical dialogue data focuses on two critical health issues: Head and Neck Cancer (HNC) and Cystic Fibrosis (NLP AI4health shared task). The proposed framework utilises a dual approach: a fine-tuned small Multilingual Text-to-Text Transfer Transformer (mT5) model for the conversational summarisation component and a fine-tuned Retrieval Augmented Generation (RAG) system integrating the dense intfloat/e5-large language model for the language-independent QA component. The efficacy of the proposed approaches is demonstrated by achieving promising precision in the QA task. Our framework achieved the highest F1 scores in QA for the three Indian languages, with F1 score of 0.3995 in Marathi, 0.7803 in Bangla, and 0.74759 in Hindi, respectively. We achieved the highest cometscore of 0.5626 on the Gujarati QA test set. For the dialogue summarisation task, our model registered the highest ROUGE-2 and ROUGE-L precision across all eight Indian languages, with English being the sole exception. These results confirm our approach potential to improve e-health in dialogue data for low-resource Indian languages."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kumar-etal-2025-saha">
<titleInfo>
<title>SAHA: Samvad AI for Healthcare Assistance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aditya</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rakesh</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Nayak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Janhavi</namePart>
<namePart type="family">Naik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dhiraj</namePart>
<namePart type="family">Bhatia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shreya</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>NLP-AI4Health</title>
</titleInfo>
<name type="personal">
<namePart type="given">Parameswari</namePart>
<namePart type="family">Krishnamurthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vandan</namePart>
<namePart type="family">Mujadia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipti</namePart>
<namePart type="family">Misra Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hannah</namePart>
<namePart type="family">Mary Thomas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mumbai, India</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-315-9</identifier>
</relatedItem>
<abstract>This paper deals with the dual task of developing a medical question answering (QA) system and generating concise summaries of medical dialogue data across nine languages (English and eight Indian languages). The medical dialogue data focuses on two critical health issues: Head and Neck Cancer (HNC) and Cystic Fibrosis (NLP AI4health shared task). The proposed framework utilises a dual approach: a fine-tuned small Multilingual Text-to-Text Transfer Transformer (mT5) model for the conversational summarisation component and a fine-tuned Retrieval Augmented Generation (RAG) system integrating the dense intfloat/e5-large language model for the language-independent QA component. The efficacy of the proposed approaches is demonstrated by achieving promising precision in the QA task. Our framework achieved the highest F1 scores in QA for the three Indian languages, with F1 score of 0.3995 in Marathi, 0.7803 in Bangla, and 0.74759 in Hindi, respectively. We achieved the highest cometscore of 0.5626 on the Gujarati QA test set. For the dialogue summarisation task, our model registered the highest ROUGE-2 and ROUGE-L precision across all eight Indian languages, with English being the sole exception. These results confirm our approach potential to improve e-health in dialogue data for low-resource Indian languages.</abstract>
<identifier type="citekey">kumar-etal-2025-saha</identifier>
<location>
<url>https://aclanthology.org/2025.nlpai4health-main.8/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>80</start>
<end>85</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SAHA: Samvad AI for Healthcare Assistance
%A Kumar, Aditya
%A Nayak, Rakesh Kumar
%A Naik, Janhavi
%A Kumar, Ritesh
%A Bhatia, Dhiraj
%A Agarwal, Shreya
%Y Krishnamurthy, Parameswari
%Y Mujadia, Vandan
%Y Misra Sharma, Dipti
%Y Mary Thomas, Hannah
%S NLP-AI4Health
%D 2025
%8 December
%I Association for Computational Linguistics
%C Mumbai, India
%@ 979-8-89176-315-9
%F kumar-etal-2025-saha
%X This paper deals with the dual task of developing a medical question answering (QA) system and generating concise summaries of medical dialogue data across nine languages (English and eight Indian languages). The medical dialogue data focuses on two critical health issues: Head and Neck Cancer (HNC) and Cystic Fibrosis (NLP AI4health shared task). The proposed framework utilises a dual approach: a fine-tuned small Multilingual Text-to-Text Transfer Transformer (mT5) model for the conversational summarisation component and a fine-tuned Retrieval Augmented Generation (RAG) system integrating the dense intfloat/e5-large language model for the language-independent QA component. The efficacy of the proposed approaches is demonstrated by achieving promising precision in the QA task. Our framework achieved the highest F1 scores in QA for the three Indian languages, with F1 score of 0.3995 in Marathi, 0.7803 in Bangla, and 0.74759 in Hindi, respectively. We achieved the highest cometscore of 0.5626 on the Gujarati QA test set. For the dialogue summarisation task, our model registered the highest ROUGE-2 and ROUGE-L precision across all eight Indian languages, with English being the sole exception. These results confirm our approach potential to improve e-health in dialogue data for low-resource Indian languages.
%U https://aclanthology.org/2025.nlpai4health-main.8/
%P 80-85
Markdown (Informal)
[SAHA: Samvad AI for Healthcare Assistance](https://aclanthology.org/2025.nlpai4health-main.8/) (Kumar et al., NLP-AI4Health 2025)
ACL
- Aditya Kumar, Rakesh Kumar Nayak, Janhavi Naik, Ritesh Kumar, Dhiraj Bhatia, and Shreya Agarwal. 2025. SAHA: Samvad AI for Healthcare Assistance. In NLP-AI4Health, pages 80–85, Mumbai, India. Association for Computational Linguistics.