The Power of Character N-grams in Native Language Identification

Artur Kulmizev, Bo Blankers, Johannes Bjerva, Malvina Nissim, Gertjan van Noord, Barbara Plank, Martijn Wieling


Abstract
In this paper, we explore the performance of a linear SVM trained on language independent character features for the NLI Shared Task 2017. Our basic system (GRONINGEN) achieves the best performance (87.56 F1-score) on the evaluation set using only 1-9 character n-grams as features. We compare this against several ensemble and meta-classifiers in order to examine how the linear system fares when combined with other, especially non-linear classifiers. Special emphasis is placed on the topic bias that exists by virtue of the assessment essay prompt distribution.
Anthology ID:
W17-5043
Volume:
Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications
Month:
September
Year:
2017
Address:
Copenhagen, Denmark
Venues:
BEA | WS
SIG:
SIGEDU
Publisher:
Association for Computational Linguistics
Note:
Pages:
382–389
Language:
URL:
https://www.aclweb.org/anthology/W17-5043
DOI:
10.18653/v1/W17-5043
Bib Export formats:
BibTeX MODS XML EndNote
PDF:
http://aclanthology.lst.uni-saarland.de/W17-5043.pdf