@inproceedings{charan-etal-2026-thunderbolts,
title = "Thunderbolts at {\#}{SMM}4{H}-{H}ea{RD} 2026: Detection of Insomnia in Clinical Notes using Transformers",
author = "Charan, Guddanti Venkata Sree and
Nama{\_}Ss@Cs.Iitr.Ac.In, Nama{\_}Ss@Cs.Iitr.Ac.In and
Sharma, Raksha and
Murthy, Rudra",
editor = "Lopez-Garcia, Guillermo and
Gonzalez-Hernandez, Graciela",
booktitle = "Proceedings of the 11th Social Media Mining for Health Research and Applications ({SMM}4{H}-{H}ea{RD} 2026) Workshop and Shared Tasks",
month = jul,
year = "2026",
address = "San Diego, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.smm4h-1.43/",
pages = "264--267",
ISBN = "979-8-89176-432-3",
abstract = "We present the SuSh system for Subtask 1 of the MultiClinAI shared task at the 11th SMM4H and HeaRD Workshop (ACL 2026), which addresses multilingual clinical named entity recognition (NER) across seven languages. Our system adopts a fully zero-shot approach using GLiNER-biomed-large-v1.0, a span-based NER model pre-trained on biomedical text, requiring no task-specific fine-tuning or labeled data in target languages. We apply a character-level sliding window strategy to handle long clinical documents that exceed the model{'}s token limit and incorporate a post processing pipeline including threshold optimization via F1-max sweep, entity-specific gazetteer lookup derived from DisTEMIST and SympTEMIST terminology lists, span boundary correction, and negation filtering. Our official submission achieves a Strict F1 of 0.5175, Strict Precision of 0.5536, Strict Recall of 0.4859, and CHR F1 of 0.6130 on the English disease subtask, demonstrating that domain adapted zero-shot biomedical NER models can serve as competitive baselines for multilingual026 clinical entity recognition without any task specific training data."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="charan-etal-2026-thunderbolts">
<titleInfo>
<title>Thunderbolts at #SMM4H-HeaRD 2026: Detection of Insomnia in Clinical Notes using Transformers</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guddanti</namePart>
<namePart type="given">Venkata</namePart>
<namePart type="given">Sree</namePart>
<namePart type="family">Charan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nama_Ss@Cs.Iitr.Ac.In</namePart>
<namePart type="family">Nama_Ss@Cs.Iitr.Ac.In</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raksha</namePart>
<namePart type="family">Sharma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rudra</namePart>
<namePart type="family">Murthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guillermo</namePart>
<namePart type="family">Lopez-Garcia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graciela</namePart>
<namePart type="family">Gonzalez-Hernandez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-432-3</identifier>
</relatedItem>
<abstract>We present the SuSh system for Subtask 1 of the MultiClinAI shared task at the 11th SMM4H and HeaRD Workshop (ACL 2026), which addresses multilingual clinical named entity recognition (NER) across seven languages. Our system adopts a fully zero-shot approach using GLiNER-biomed-large-v1.0, a span-based NER model pre-trained on biomedical text, requiring no task-specific fine-tuning or labeled data in target languages. We apply a character-level sliding window strategy to handle long clinical documents that exceed the model’s token limit and incorporate a post processing pipeline including threshold optimization via F1-max sweep, entity-specific gazetteer lookup derived from DisTEMIST and SympTEMIST terminology lists, span boundary correction, and negation filtering. Our official submission achieves a Strict F1 of 0.5175, Strict Precision of 0.5536, Strict Recall of 0.4859, and CHR F1 of 0.6130 on the English disease subtask, demonstrating that domain adapted zero-shot biomedical NER models can serve as competitive baselines for multilingual026 clinical entity recognition without any task specific training data.</abstract>
<identifier type="citekey">charan-etal-2026-thunderbolts</identifier>
<location>
<url>https://aclanthology.org/2026.smm4h-1.43/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>264</start>
<end>267</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Thunderbolts at #SMM4H-HeaRD 2026: Detection of Insomnia in Clinical Notes using Transformers
%A Charan, Guddanti Venkata Sree
%A Nama_Ss@Cs.Iitr.Ac.In, Nama_Ss@Cs.Iitr.Ac.In
%A Sharma, Raksha
%A Murthy, Rudra
%Y Lopez-Garcia, Guillermo
%Y Gonzalez-Hernandez, Graciela
%S Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, United States
%@ 979-8-89176-432-3
%F charan-etal-2026-thunderbolts
%X We present the SuSh system for Subtask 1 of the MultiClinAI shared task at the 11th SMM4H and HeaRD Workshop (ACL 2026), which addresses multilingual clinical named entity recognition (NER) across seven languages. Our system adopts a fully zero-shot approach using GLiNER-biomed-large-v1.0, a span-based NER model pre-trained on biomedical text, requiring no task-specific fine-tuning or labeled data in target languages. We apply a character-level sliding window strategy to handle long clinical documents that exceed the model’s token limit and incorporate a post processing pipeline including threshold optimization via F1-max sweep, entity-specific gazetteer lookup derived from DisTEMIST and SympTEMIST terminology lists, span boundary correction, and negation filtering. Our official submission achieves a Strict F1 of 0.5175, Strict Precision of 0.5536, Strict Recall of 0.4859, and CHR F1 of 0.6130 on the English disease subtask, demonstrating that domain adapted zero-shot biomedical NER models can serve as competitive baselines for multilingual026 clinical entity recognition without any task specific training data.
%U https://aclanthology.org/2026.smm4h-1.43/
%P 264-267
Markdown (Informal)
[Thunderbolts at #SMM4H-HeaRD 2026: Detection of Insomnia in Clinical Notes using Transformers](https://aclanthology.org/2026.smm4h-1.43/) (Charan et al., SMM4H 2026)
ACL