@inproceedings{van-es-2026-dt4h,
title = "{DT}4{H}.nl at {\#}{SMM}4{H}-{H}ea{RD} 2026: Multilingual Clinical {NER} with multilingual and monolingual models",
author = "van Es, Bram",
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-1.14/",
pages = "82--87",
ISBN = "979-8-89176-432-3",
abstract = "We describe the setup we used to complete the MultiClinAI-NER task in the SMM4H-HeaRD workshop 2026. In this work we employed a dedicated multilingual encoder model (EuroBERT-610m), two Dutch encoder models trained from scratch on clinical corpora (MedRoBERTa.nl and CardioDeBERTa.nl) and a generic Dutch encoder model (RobBERT2023-large), all finetuned with a 3-layer DNN head. We find that the use of multilingual datasets is potentially beneficial in augmenting the training corpora of monolingual models."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-es-2026-dt4h">
<titleInfo>
<title>DT4H.nl at #SMM4H-HeaRD 2026: Multilingual Clinical NER with multilingual and monolingual models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bram</namePart>
<namePart type="family">van Es</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 describe the setup we used to complete the MultiClinAI-NER task in the SMM4H-HeaRD workshop 2026. In this work we employed a dedicated multilingual encoder model (EuroBERT-610m), two Dutch encoder models trained from scratch on clinical corpora (MedRoBERTa.nl and CardioDeBERTa.nl) and a generic Dutch encoder model (RobBERT2023-large), all finetuned with a 3-layer DNN head. We find that the use of multilingual datasets is potentially beneficial in augmenting the training corpora of monolingual models.</abstract>
<identifier type="citekey">van-es-2026-dt4h</identifier>
<location>
<url>https://aclanthology.org/2026.smm4h-1.14/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>82</start>
<end>87</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DT4H.nl at #SMM4H-HeaRD 2026: Multilingual Clinical NER with multilingual and monolingual models
%A van Es, Bram
%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 van-es-2026-dt4h
%X We describe the setup we used to complete the MultiClinAI-NER task in the SMM4H-HeaRD workshop 2026. In this work we employed a dedicated multilingual encoder model (EuroBERT-610m), two Dutch encoder models trained from scratch on clinical corpora (MedRoBERTa.nl and CardioDeBERTa.nl) and a generic Dutch encoder model (RobBERT2023-large), all finetuned with a 3-layer DNN head. We find that the use of multilingual datasets is potentially beneficial in augmenting the training corpora of monolingual models.
%U https://aclanthology.org/2026.smm4h-1.14/
%P 82-87
Markdown (Informal)
[DT4H.nl at #SMM4H-HeaRD 2026: Multilingual Clinical NER with multilingual and monolingual models](https://aclanthology.org/2026.smm4h-1.14/) (van Es, SMM4H 2026)
ACL