@inproceedings{toma-popescu-2026-well,
title = "How Well Do Language Models Handle {R}omanian Diacritics? A Comparison of Monolingual and Multilingual Architectures",
author = "Toma, Alexandra and
Popescu, Maria Cristina",
editor = "Ranaldi, Leonardo and
Pucci, Giulia and
Ranaldi, Federico and
Valentino, Marco and
Birch, Alexandra and
Zanzotto, Fabio Massimo",
booktitle = "The Proceedings of the Workshop on Open Reasoning Across Cultures Languages ({ORACLE})",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.oracle-main.15/",
pages = "234--245",
ISBN = "979-8-89176-483-5",
abstract = "Romanian orthography relies on five diacritic characters ({\u{a}}, {\^i}, {\^a}, {\c{s}}, {\c{t}}) that are frequently omitted in informal digital text, yet the impact of text cleaning decisions regarding diacritics on Romanian language models has not been systematically studied across architectures and tasks. We address this gap by examining how diacritics affect subword tokenization, contextual embeddings, and three downstream tasks - POS tagging, named entity recognition, and semantic textual similarity - comparing Romanian BERT with mBERT, DistilmBERT, and mT5. Each model is fine-tuned on diacriticpreserving and diacritic-stripped data and evaluated on both, isolating both overall performance and robustness to train{--}test mismatch. This work provides the first systematic, multitask account of how diacritic effects propagate from tokenization to downstream performance, showing this depends jointly on pretraining corpus and architecture, and offers practical guidance for Romanian NLP systems that must handle diacritic-inconsistent text."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="toma-popescu-2026-well">
<titleInfo>
<title>How Well Do Language Models Handle Romanian Diacritics? A Comparison of Monolingual and Multilingual Architectures</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Toma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Cristina</namePart>
<namePart type="family">Popescu</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>The Proceedings of the Workshop on Open Reasoning Across Cultures Languages (ORACLE)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Leonardo</namePart>
<namePart type="family">Ranaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giulia</namePart>
<namePart type="family">Pucci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Federico</namePart>
<namePart type="family">Ranaldi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Valentino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Birch</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fabio</namePart>
<namePart type="given">Massimo</namePart>
<namePart type="family">Zanzotto</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">979-8-89176-483-5</identifier>
</relatedItem>
<abstract>Romanian orthography relies on five diacritic characters (ă, î, â, ş, ţ) that are frequently omitted in informal digital text, yet the impact of text cleaning decisions regarding diacritics on Romanian language models has not been systematically studied across architectures and tasks. We address this gap by examining how diacritics affect subword tokenization, contextual embeddings, and three downstream tasks - POS tagging, named entity recognition, and semantic textual similarity - comparing Romanian BERT with mBERT, DistilmBERT, and mT5. Each model is fine-tuned on diacriticpreserving and diacritic-stripped data and evaluated on both, isolating both overall performance and robustness to train–test mismatch. This work provides the first systematic, multitask account of how diacritic effects propagate from tokenization to downstream performance, showing this depends jointly on pretraining corpus and architecture, and offers practical guidance for Romanian NLP systems that must handle diacritic-inconsistent text.</abstract>
<identifier type="citekey">toma-popescu-2026-well</identifier>
<location>
<url>https://aclanthology.org/2026.oracle-main.15/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>234</start>
<end>245</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T How Well Do Language Models Handle Romanian Diacritics? A Comparison of Monolingual and Multilingual Architectures
%A Toma, Alexandra
%A Popescu, Maria Cristina
%Y Ranaldi, Leonardo
%Y Pucci, Giulia
%Y Ranaldi, Federico
%Y Valentino, Marco
%Y Birch, Alexandra
%Y Zanzotto, Fabio Massimo
%S The Proceedings of the Workshop on Open Reasoning Across Cultures Languages (ORACLE)
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-483-5
%F toma-popescu-2026-well
%X Romanian orthography relies on five diacritic characters (ă, î, â, ş, ţ) that are frequently omitted in informal digital text, yet the impact of text cleaning decisions regarding diacritics on Romanian language models has not been systematically studied across architectures and tasks. We address this gap by examining how diacritics affect subword tokenization, contextual embeddings, and three downstream tasks - POS tagging, named entity recognition, and semantic textual similarity - comparing Romanian BERT with mBERT, DistilmBERT, and mT5. Each model is fine-tuned on diacriticpreserving and diacritic-stripped data and evaluated on both, isolating both overall performance and robustness to train–test mismatch. This work provides the first systematic, multitask account of how diacritic effects propagate from tokenization to downstream performance, showing this depends jointly on pretraining corpus and architecture, and offers practical guidance for Romanian NLP systems that must handle diacritic-inconsistent text.
%U https://aclanthology.org/2026.oracle-main.15/
%P 234-245
Markdown (Informal)
[How Well Do Language Models Handle Romanian Diacritics? A Comparison of Monolingual and Multilingual Architectures](https://aclanthology.org/2026.oracle-main.15/) (Toma & Popescu, ORACLE 2026)
ACL