@inproceedings{roy-das-2025-nlp4health,
title = "{NLP}4{H}ealth: Multilingual Clinical Dialogue Summarization and {QA} with m{T}5 and {L}o{RA}",
author = "Roy, Moutushi and
Das, Dipankar",
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.10/",
pages = "93--97",
ISBN = "979-8-89176-315-9",
abstract = "In this work, we present NLP4Health, a unified and reproducible pipeline to accomplish the tasks of multilingual clinical dialogue summarization and question answering (QA). Our system fine-tunes the multilingual sequence-to-sequence model google/mt5-base along with parameter-efficient Low-Rank Adaptation (LoRA) modules to support ten Indian languages. For each clinical dialogue, the model produces (1) a free-text English summary, (2) an English structured key{--}value (KnV) JSON summary, and (3) QA responses in the dialogue{'}s original language. We conducted preprocessing, fine-tuning, and inference, and evaluated across QA, textual, and structured metrics, analyzing performance in low-resource settings. The adapter weights, tokenizer, and inference scripts are publicly released to promote transparency and reproducibility."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="roy-das-2025-nlp4health">
<titleInfo>
<title>NLP4Health: Multilingual Clinical Dialogue Summarization and QA with mT5 and LoRA</title>
</titleInfo>
<name type="personal">
<namePart type="given">Moutushi</namePart>
<namePart type="family">Roy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dipankar</namePart>
<namePart type="family">Das</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>In this work, we present NLP4Health, a unified and reproducible pipeline to accomplish the tasks of multilingual clinical dialogue summarization and question answering (QA). Our system fine-tunes the multilingual sequence-to-sequence model google/mt5-base along with parameter-efficient Low-Rank Adaptation (LoRA) modules to support ten Indian languages. For each clinical dialogue, the model produces (1) a free-text English summary, (2) an English structured key–value (KnV) JSON summary, and (3) QA responses in the dialogue’s original language. We conducted preprocessing, fine-tuning, and inference, and evaluated across QA, textual, and structured metrics, analyzing performance in low-resource settings. The adapter weights, tokenizer, and inference scripts are publicly released to promote transparency and reproducibility.</abstract>
<identifier type="citekey">roy-das-2025-nlp4health</identifier>
<location>
<url>https://aclanthology.org/2025.nlpai4health-main.10/</url>
</location>
<part>
<date>2025-12</date>
<extent unit="page">
<start>93</start>
<end>97</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NLP4Health: Multilingual Clinical Dialogue Summarization and QA with mT5 and LoRA
%A Roy, Moutushi
%A Das, Dipankar
%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 roy-das-2025-nlp4health
%X In this work, we present NLP4Health, a unified and reproducible pipeline to accomplish the tasks of multilingual clinical dialogue summarization and question answering (QA). Our system fine-tunes the multilingual sequence-to-sequence model google/mt5-base along with parameter-efficient Low-Rank Adaptation (LoRA) modules to support ten Indian languages. For each clinical dialogue, the model produces (1) a free-text English summary, (2) an English structured key–value (KnV) JSON summary, and (3) QA responses in the dialogue’s original language. We conducted preprocessing, fine-tuning, and inference, and evaluated across QA, textual, and structured metrics, analyzing performance in low-resource settings. The adapter weights, tokenizer, and inference scripts are publicly released to promote transparency and reproducibility.
%U https://aclanthology.org/2025.nlpai4health-main.10/
%P 93-97
Markdown (Informal)
[NLP4Health: Multilingual Clinical Dialogue Summarization and QA with mT5 and LoRA](https://aclanthology.org/2025.nlpai4health-main.10/) (Roy & Das, NLP-AI4Health 2025)
ACL