@inproceedings{vassileva-etal-2026-enigma,
title = "Enigma at {\#}{SMM}4{H}{--}{H}ea{RD} 2026: Leveraging Multilingual Pre-trained Models for Clinical Named Entity Recognition",
author = "Vassileva, Sylvia and
Ilieva, Plamena and
Kostadinov, Teodor Svetoslavov and
Petkova, Monika Peteva and
Manchevski, Daniel and
Doynov, Vitosh and
Koychev, Ivan and
Boytcheva, Svetla",
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-1.19/",
pages = "113--120",
ISBN = "979-8-89176-432-3",
abstract = "This paper addresses the MultiClinAI challenge, subtask MultiClinNER, which focuses on clinical Named Entity Recognition (NER) across seven languages: Czech, Dutch, English, Italian, Romanian, Spanish, and Swedish. The main goal of MultiClinNER is to identify and extract clinical terms specifically related to diseases, procedures, and symptoms from discharge summaries. The paper explores a variety of state-of-the-art methods, both monolingual and multilingual, ranging from pretrained, zero-shot, domain-adapted transformers to fine-tuned transformer models, and demonstrates the benefits of ensemble modeling. Data augmentation through external resources significantly enhanced the models' ability to recognize clinical entities. Both monolingual and multilingual approaches showed complementary strengths depending on the language and entity type. The average F1 score achieved across the best models for each language and category is 0.6502."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vassileva-etal-2026-enigma">
<titleInfo>
<title>Enigma at #SMM4H–HeaRD 2026: Leveraging Multilingual Pre-trained Models for Clinical Named Entity Recognition</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sylvia</namePart>
<namePart type="family">Vassileva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Plamena</namePart>
<namePart type="family">Ilieva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Teodor</namePart>
<namePart type="given">Svetoslavov</namePart>
<namePart type="family">Kostadinov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Monika</namePart>
<namePart type="given">Peteva</namePart>
<namePart type="family">Petkova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Manchevski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vitosh</namePart>
<namePart type="family">Doynov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="family">Koychev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Svetla</namePart>
<namePart type="family">Boytcheva</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>This paper addresses the MultiClinAI challenge, subtask MultiClinNER, which focuses on clinical Named Entity Recognition (NER) across seven languages: Czech, Dutch, English, Italian, Romanian, Spanish, and Swedish. The main goal of MultiClinNER is to identify and extract clinical terms specifically related to diseases, procedures, and symptoms from discharge summaries. The paper explores a variety of state-of-the-art methods, both monolingual and multilingual, ranging from pretrained, zero-shot, domain-adapted transformers to fine-tuned transformer models, and demonstrates the benefits of ensemble modeling. Data augmentation through external resources significantly enhanced the models’ ability to recognize clinical entities. Both monolingual and multilingual approaches showed complementary strengths depending on the language and entity type. The average F1 score achieved across the best models for each language and category is 0.6502.</abstract>
<identifier type="citekey">vassileva-etal-2026-enigma</identifier>
<location>
<url>https://aclanthology.org/2026.smm4h-1.19/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>113</start>
<end>120</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Enigma at #SMM4H–HeaRD 2026: Leveraging Multilingual Pre-trained Models for Clinical Named Entity Recognition
%A Vassileva, Sylvia
%A Ilieva, Plamena
%A Kostadinov, Teodor Svetoslavov
%A Petkova, Monika Peteva
%A Manchevski, Daniel
%A Doynov, Vitosh
%A Koychev, Ivan
%A Boytcheva, Svetla
%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 vassileva-etal-2026-enigma
%X This paper addresses the MultiClinAI challenge, subtask MultiClinNER, which focuses on clinical Named Entity Recognition (NER) across seven languages: Czech, Dutch, English, Italian, Romanian, Spanish, and Swedish. The main goal of MultiClinNER is to identify and extract clinical terms specifically related to diseases, procedures, and symptoms from discharge summaries. The paper explores a variety of state-of-the-art methods, both monolingual and multilingual, ranging from pretrained, zero-shot, domain-adapted transformers to fine-tuned transformer models, and demonstrates the benefits of ensemble modeling. Data augmentation through external resources significantly enhanced the models’ ability to recognize clinical entities. Both monolingual and multilingual approaches showed complementary strengths depending on the language and entity type. The average F1 score achieved across the best models for each language and category is 0.6502.
%U https://aclanthology.org/2026.smm4h-1.19/
%P 113-120
Markdown (Informal)
[Enigma at #SMM4H–HeaRD 2026: Leveraging Multilingual Pre-trained Models for Clinical Named Entity Recognition](https://aclanthology.org/2026.smm4h-1.19/) (Vassileva et al., SMM4H 2026)
ACL
- Sylvia Vassileva, Plamena Ilieva, Teodor Svetoslavov Kostadinov, Monika Peteva Petkova, Daniel Manchevski, Vitosh Doynov, Ivan Koychev, and Svetla Boytcheva. 2026. Enigma at #SMM4H–HeaRD 2026: Leveraging Multilingual Pre-trained Models for Clinical Named Entity Recognition. In Proceedings of the 11th Social Media Mining for Health Research and Applications (SMM4H-HeaRD 2026) Workshop and Shared Tasks, pages 113–120, San Diego, United States. Association for Computational Linguistics.