Sari la conținut

Invited Lecturer: EUROLAN 2025

At the EUROLAN-2025 Summer School on NLP in the Age of Complex Networks and Agentic AI (14-20 September 2025, Timișoara & online), I contributed two sessions focusing on how corpus-based natural language processing can generate insights for education and learning analytics.

More information here.

Tutorial (together with Andreea Dinca and Karla Csürös):

This lecture introduced participants to the development of corpus-driven NLP applications aimed at extracting educational insights from Romanian-language data. I presented several platforms, i.e. ROGER, EXPRES, and LEMI, that support advanced linguistic analysis and pedagogical applications. ROGER and EXPRES are academic writing platforms designed for exploring rhetorical moves, academic phraseology, and discourse patterns using annotated corpora and n-gram analysis. LEMI, a readability assessment tool for children’s literature, integrates lexical and syntactic complexity metrics to guide age-appropriate text selection. The tutorial emphasized corpus compilation, annotation schemes, feature engineering, and the integration of linguistic insights into educational NLP pipelines.

Practical Session (together with Andreea Dinca and Karla Csürös):

In the hands-on workshop, participants applied NLP and data mining techniques to analyze Romanian school textbooks using data from the ROTEX corpus. Together, we explored how instructional tasks reflect cognitive complexity based on Bloom’s Taxonomy, comparing materials across grades and publishers. Through POS tagging, pattern matching, and task classification, participants learned how computational methods can assess educational content quality and pedagogical coherence, particularly valuable in low-resource educational contexts.

The sessions highlighted how linguistic technologies can connect text analysis with pedagogy, supporting teachers, curriculum designers, and educational researchers in making data-informed decisions about language and learning.

© 2025 Mădălina Chitez. Acest conținut este licențiat sub Creative Commons Attribution 4.0 International (CC BY 4.0).
Se permite copierea și distribuirea conținutului, cu condiția menționării sursei: www.madalinachitez.com.
Detalii licență: https://creativecommons.org/licenses/by/4.0/.