https://feralvam.github.io/tags/cefr/CEFRHugoBlox Kit (https://hugoblox.com)en-usFri, 01 May 2026 00:00:00 +0000https://feralvam.github.io/media/icon_hu_ab250a83af8ff43c.pnghttps://feralvam.github.io/tags/cefr/https://feralvam.github.io/projects/democratising-linguistic-analysis/Fri, 01 May 2026 00:00:00 +0000https://feralvam.github.io/projects/democratising-linguistic-analysis/<p>Cardiff University IAA-funded project extending Proffiliadur into a bilingual, CEFR-aware text profiling toolkit for expert and non-expert users alike.</p> <p><strong>Funder:</strong> Cardiff University IAA Fund<br> <strong>Period:</strong> May 2026 – November 2026<br> <strong>Role:</strong> Co-Investigator<br> <strong>Research theme:</strong> </p> <hr> <p>This project extends the functionality of , a digital toolkit for text profiling and readability analysis in Welsh, along three lines:</p> <ol> <li><strong>CEFR-level profiling</strong> — incorporating tools for profiling texts according to the Common European Framework of Reference, connecting Proffiliadur to the CEFR-Cymraeg prediction models and broadening its usefulness in pedagogic contexts</li> <li><strong>Bilingual analysis</strong> — integrating English-language profiling and readability tools alongside the existing Welsh ones, enabling bilingual text analysis</li> <li><strong>Public launch</strong> — releasing the toolkit for use by expert and non-expert users alike</li> </ol> <hr> <h3 id="related-projects">Related Projects</h3> <ul> <li> </li> <li> </li> <li> </li> </ul>https://feralvam.github.io/projects/cefr-cymraeg/Tue, 01 Apr 2025 00:00:00 +0000https://feralvam.github.io/projects/cefr-cymraeg/<p>Welsh Government-funded project building the first CEFR-annotated dataset and baseline models for automatically assessing the proficiency level of Welsh texts.</p> <p><strong>Funder:</strong> Welsh Government<br> <strong>Period:</strong> April 2025 – March 2026<br> <strong>Role:</strong> Co-Investigator<br> <strong>Research theme:</strong> </p> <hr> <p>Automated tools for assessing the proficiency level of Welsh learner texts have been lacking, limiting support for Welsh-language education and assessment. This project addressed that gap with two objectives:</p> <ol> <li>Collect and annotate a comprehensive dataset of Welsh texts classified by CEFR level</li> <li>Develop baseline machine learning models for predicting the CEFR level of Welsh texts</li> </ol> <p>The result, <strong>CEFR-Cymraeg</strong>, is the first CEFR-annotated language proficiency dataset for Welsh (A1–B2), together with baseline classification models, enabling automated language proficiency assessment for Welsh learners.</p> <hr> <h3 id="selected-publications">Selected Publications</h3> <ul> <li> </li> </ul>