Proffiliadur: Piloting Welsh-Language Readability Tools

May 1, 2025 · 1 min read
projects

Cardiff University IAA-funded pilot exploring the potential for sophisticated Welsh-language readability tools built on existing Welsh linguistic resources.

Funder: Cardiff University IAA Follow-on Fund
Period: May 2025 – November 2025
Role: Co-Investigator
Research theme: Welsh Language Technology & Multilingual NLP


Welsh has unique linguistic features, including initial consonant mutation, that pose significant challenges for standard NLP pipelines, and Welsh had lacked dedicated readability tools as a result. This project piloted the potential for developing sophisticated Welsh-language readability tools by building on existing Welsh resources, such as those from CorCenCC and the Geirfan word list.

The pilot produced Proffiliadur, an open-source toolkit computing 141 linguistic complexity indices for Welsh texts, supporting CEFR-level classification and accessibility analysis. Its success directly led to further funding to extend the toolkit’s functionality and reach: see Democratising Linguistic Analysis and CyTag Neural Upgrade and DigiGrid Enhancement.


Selected Publications

Fernando Alva-Manchego
Authors
Researcher in Natural Language Processing
My research interests include text simplification, readability assessment, multilingual NLP, Welsh language technology, and NLP for education and social care.