Seminarium i datorlingvistik
- Datum: –15.00
- Plats: Engelska parken Rum: 9-3042
- Föreläsare: Ildiko Pilán
- Kontaktperson: Ali Basirat
Automatic linguistic complexity analysis in the context of second language
With the ever-growing presence of electronic devices in our everyday lives, it is compelling to investigate how technology can make the language learning process more efficient and enjoyable. We explore automatic approaches for modelling linguistic complexity at different proficiency levels when learning Swedish as a second and foreign language (L2). For these purposes, we combine Natural Language Processing with supervised and semi-supervised machine learning techniques. We study linguistic complexity in two types of L2 texts, those written by experts for learners and those produced by learners themselves, and explore how one text type can be used to improve classification performance for the other. Automatic proficiency level prediction has a number of application potentials for the field of Intelligent Computer-Assisted Language Learning, out of which we investigate two directions: locating learning materials suitable for L2 learners from corpora and the automatic evaluation of L2 texts.