@inproceedings{gutierrez-rolon-etal-2026-proffiliadur,
title = "Proffiliadur: {W}elsh Language Text Profiling Toolkit",
author = "Guti{\'e}rrez-Rol{\'o}n, Nicol{\'a}s and
Davies, Jonathan and
Williams, Tomos and
Knight, Dawn and
Alva-Manchego, Fernando",
editor = "Piperidis, Stelios and
Bel, N{\'u}ria and
van den Heuvel, Henk and
Ide, Nancy and
Krek, Simon and
Toral, Antonio",
booktitle = "Proceedings of the Fifteenth Language Resources and Evaluation Conference",
month = may,
year = "2026",
address = "Palma de Mallorca, Spain",
publisher = "ELRA Language Resource Association",
url = "https://aclanthology.org/2026.lrec-1.88/",
doi = "10.63317/5c6yawn79s5h",
pages = "1129--1142",
abstract = "We introduce Proffiliadur, a Python toolkit for text profiling and readability analysis in Welsh. The toolkit computes 141 surface, lexical, morphological, and syntactic indices, designed to capture linguistic variation while incorporating a Welsh-specific tokenisation process that enables accurate morphological analysis and handles phenomena such as initial consonant mutation. Proffiliadur enables systematic assessment of text accessibility and supports applications in education, healthcare, and public communication. We demonstrate the toolkit{'}s usefulness through two complementary analyses. First, we examine texts written in accordance with the Cymraeg Cl{\^i}r ({``}Clear Welsh'') principles and compare them with regular Welsh texts. Second, we analyse texts across CEFR proficiency levels to explore how linguistic complexity varies with learner ability. We also evaluate feature-based and neural classification models for automatic complexity detection, showing that interpretable linguistic indices alone achieve strong predictive performance (F1 = 0.94), comparable to a fine-tuned transformer (F1 = 0.97). Proffiliadur provides the first dedicated text profiling toolkit for Welsh, offering reproducible, linguistically grounded measures of readability for a low-resource language."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gutierrez-rolon-etal-2026-proffiliadur">
<titleInfo>
<title>Proffiliadur: Welsh Language Text Profiling Toolkit</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicolás</namePart>
<namePart type="family">Gutiérrez-Rolón</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">Davies</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tomos</namePart>
<namePart type="family">Williams</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dawn</namePart>
<namePart type="family">Knight</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="family">Alva-Manchego</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Fifteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Núria</namePart>
<namePart type="family">Bel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Henk</namePart>
<namePart type="family">van den Heuvel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nancy</namePart>
<namePart type="family">Ide</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Simon</namePart>
<namePart type="family">Krek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Antonio</namePart>
<namePart type="family">Toral</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resource Association</publisher>
<place>
<placeTerm type="text">Palma de Mallorca, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We introduce Proffiliadur, a Python toolkit for text profiling and readability analysis in Welsh. The toolkit computes 141 surface, lexical, morphological, and syntactic indices, designed to capture linguistic variation while incorporating a Welsh-specific tokenisation process that enables accurate morphological analysis and handles phenomena such as initial consonant mutation. Proffiliadur enables systematic assessment of text accessibility and supports applications in education, healthcare, and public communication. We demonstrate the toolkit’s usefulness through two complementary analyses. First, we examine texts written in accordance with the Cymraeg Clîr (“Clear Welsh”) principles and compare them with regular Welsh texts. Second, we analyse texts across CEFR proficiency levels to explore how linguistic complexity varies with learner ability. We also evaluate feature-based and neural classification models for automatic complexity detection, showing that interpretable linguistic indices alone achieve strong predictive performance (F1 = 0.94), comparable to a fine-tuned transformer (F1 = 0.97). Proffiliadur provides the first dedicated text profiling toolkit for Welsh, offering reproducible, linguistically grounded measures of readability for a low-resource language.</abstract>
<identifier type="citekey">gutierrez-rolon-etal-2026-proffiliadur</identifier>
<identifier type="doi">10.63317/5c6yawn79s5h</identifier>
<location>
<url>https://aclanthology.org/2026.lrec-1.88/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>1129</start>
<end>1142</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Proffiliadur: Welsh Language Text Profiling Toolkit
%A Gutiérrez-Rolón, Nicolás
%A Davies, Jonathan
%A Williams, Tomos
%A Knight, Dawn
%A Alva-Manchego, Fernando
%Y Piperidis, Stelios
%Y Bel, Núria
%Y van den Heuvel, Henk
%Y Ide, Nancy
%Y Krek, Simon
%Y Toral, Antonio
%S Proceedings of the Fifteenth Language Resources and Evaluation Conference
%D 2026
%8 May
%I ELRA Language Resource Association
%C Palma de Mallorca, Spain
%F gutierrez-rolon-etal-2026-proffiliadur
%X We introduce Proffiliadur, a Python toolkit for text profiling and readability analysis in Welsh. The toolkit computes 141 surface, lexical, morphological, and syntactic indices, designed to capture linguistic variation while incorporating a Welsh-specific tokenisation process that enables accurate morphological analysis and handles phenomena such as initial consonant mutation. Proffiliadur enables systematic assessment of text accessibility and supports applications in education, healthcare, and public communication. We demonstrate the toolkit’s usefulness through two complementary analyses. First, we examine texts written in accordance with the Cymraeg Clîr (“Clear Welsh”) principles and compare them with regular Welsh texts. Second, we analyse texts across CEFR proficiency levels to explore how linguistic complexity varies with learner ability. We also evaluate feature-based and neural classification models for automatic complexity detection, showing that interpretable linguistic indices alone achieve strong predictive performance (F1 = 0.94), comparable to a fine-tuned transformer (F1 = 0.97). Proffiliadur provides the first dedicated text profiling toolkit for Welsh, offering reproducible, linguistically grounded measures of readability for a low-resource language.
%R 10.63317/5c6yawn79s5h
%U https://aclanthology.org/2026.lrec-1.88/
%U https://doi.org/10.63317/5c6yawn79s5h
%P 1129-1142
Markdown (Informal)
[Proffiliadur: Welsh Language Text Profiling Toolkit](https://aclanthology.org/2026.lrec-1.88/) (Gutiérrez-Rolón et al., LREC 2026)
ACL
- Nicolás Gutiérrez-Rolón, Jonathan Davies, Tomos Williams, Dawn Knight, and Fernando Alva-Manchego. 2026. Proffiliadur: Welsh Language Text Profiling Toolkit. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 1129–1142, Palma de Mallorca, Spain. ELRA Language Resource Association.