Iria Iria del Río
University of Lisbon, Center of Linguistics - CLUL, Portugal
Download article
Published in: Proceedings of the 8th Workshop on Natural Language Processing for Computer Assisted Language Learning (NLP4CALL 2019), September 30, Turku Finland
Linköping Electronic Conference Proceedings 164:4, p. 31-40
NEALT Proceedings Series 39:4, p. 31-40
Published: 2019-09-30
ISBN: 978-91-7929-998-9
ISSN: 1650-3686 (print), 1650-3740 (online)
This work explores the relationship between L2 proficiency levels and certain linguistic features through experiments in automatic proficiency classification. We use L2 Spanish and L2 Portuguese data and perform monolingual and
cross-lingual experiments. We also compare native and leaner Spanish texts. To
the best of our knowledge, this is the first
work that performs automatic proficiency
classification for L2 Spanish, as well as
cross-lingual proficiency classification between L2 Portuguese and L2 Spanish.
Our results for L2 Spanish are similar
to the state-of-the-art, while our cross-lingual experiments got lower results than
similar works. In general, all the experiments suggest new insights about the relationship between linguistic features and
proficiency levels in L2 Portuguese and L2
Spanish.
Automatic Proficiency Classification, L2 Spanish, L2 Portuguese, Second Language Acquisition
