@inproceedings{trautner-thomas-2026-nerqual,
title = "{NERQ}ual: Evaluating the Robustness of Named Entity Recognition Models to Data Quality Issues",
author = "Trautner, Denis and
Thomas, Philippe",
editor = "Bak, JinYeong and
van der Goot, Rob and
Jang, Hyeju and
Buaphet, Weerayut and
Ramponi, Alan and
Xu, Wei and
Ritter, Alan",
booktitle = "Proceedings of the 11th Workshop on Natural User-generated Text",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.wnut-1.14/",
pages = "195--209",
ISBN = "979-8-89176-470-5",
abstract = "Transformer-based models for Named Entity Recognition (NER) achieve strong performance on clean benchmarks, yet their reliability in real-world settings remains insufficiently understood. In practical applications, NER systems are frequently exposed to degraded input originating from optical character recognition, automatic speech recognition, and user-generated text. We address this gap by deriving a taxonomy of data quality perturbations from a systematic literature review, consolidating fragmented prior work into a unified framework. Guided by this taxonomy, we conduct controlled experiments evaluating six widely used transformer architectures under varying perturbation types, intensities, and training configurations. Our results show that syntactic perturbations cause the most severe performance degradation across models, while architectural features such as character-level processing and disentangled attention confer specific robustness advantages. Furthermore, we demonstrate that targeted training with perturbed data can recover more than half of the lost performance with minimal impact on clean-data accuracy."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="trautner-thomas-2026-nerqual">
<titleInfo>
<title>NERQual: Evaluating the Robustness of Named Entity Recognition Models to Data Quality Issues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Denis</namePart>
<namePart type="family">Trautner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Thomas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 11th Workshop on Natural User-generated Text</title>
</titleInfo>
<name type="personal">
<namePart type="given">JinYeong</namePart>
<namePart type="family">Bak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rob</namePart>
<namePart type="family">van der Goot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hyeju</namePart>
<namePart type="family">Jang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weerayut</namePart>
<namePart type="family">Buaphet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ramponi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-470-5</identifier>
</relatedItem>
<abstract>Transformer-based models for Named Entity Recognition (NER) achieve strong performance on clean benchmarks, yet their reliability in real-world settings remains insufficiently understood. In practical applications, NER systems are frequently exposed to degraded input originating from optical character recognition, automatic speech recognition, and user-generated text. We address this gap by deriving a taxonomy of data quality perturbations from a systematic literature review, consolidating fragmented prior work into a unified framework. Guided by this taxonomy, we conduct controlled experiments evaluating six widely used transformer architectures under varying perturbation types, intensities, and training configurations. Our results show that syntactic perturbations cause the most severe performance degradation across models, while architectural features such as character-level processing and disentangled attention confer specific robustness advantages. Furthermore, we demonstrate that targeted training with perturbed data can recover more than half of the lost performance with minimal impact on clean-data accuracy.</abstract>
<identifier type="citekey">trautner-thomas-2026-nerqual</identifier>
<location>
<url>https://aclanthology.org/2026.wnut-1.14/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>195</start>
<end>209</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NERQual: Evaluating the Robustness of Named Entity Recognition Models to Data Quality Issues
%A Trautner, Denis
%A Thomas, Philippe
%Y Bak, JinYeong
%Y van der Goot, Rob
%Y Jang, Hyeju
%Y Buaphet, Weerayut
%Y Ramponi, Alan
%Y Xu, Wei
%Y Ritter, Alan
%S Proceedings of the 11th Workshop on Natural User-generated Text
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-470-5
%F trautner-thomas-2026-nerqual
%X Transformer-based models for Named Entity Recognition (NER) achieve strong performance on clean benchmarks, yet their reliability in real-world settings remains insufficiently understood. In practical applications, NER systems are frequently exposed to degraded input originating from optical character recognition, automatic speech recognition, and user-generated text. We address this gap by deriving a taxonomy of data quality perturbations from a systematic literature review, consolidating fragmented prior work into a unified framework. Guided by this taxonomy, we conduct controlled experiments evaluating six widely used transformer architectures under varying perturbation types, intensities, and training configurations. Our results show that syntactic perturbations cause the most severe performance degradation across models, while architectural features such as character-level processing and disentangled attention confer specific robustness advantages. Furthermore, we demonstrate that targeted training with perturbed data can recover more than half of the lost performance with minimal impact on clean-data accuracy.
%U https://aclanthology.org/2026.wnut-1.14/
%P 195-209
Markdown (Informal)
[NERQual: Evaluating the Robustness of Named Entity Recognition Models to Data Quality Issues](https://aclanthology.org/2026.wnut-1.14/) (Trautner & Thomas, WNUT 2026)
ACL