Can string kernels pass the test of time in Native Language Identification?

Radu Tudor Ionescu, Marius Popescu
2017 Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications  
We describe a machine learning approach for the 2017 shared task on Native Language Identification (NLI). The proposed approach combines several kernels using multiple kernel learning. While most of our kernels are based on character p-grams (also known as n-grams) extracted from essays or speech transcripts, we also use a kernel based on i-vectors, a low-dimensional representation of audio recordings, provided by the shared task organizers. For the learning stage, we choose Kernel Discriminant
more » ... Kernel Discriminant Analysis (KDA) over Kernel Ridge Regression (KRR), because the former classifier obtains better results than the latter one on the development set. In our previous work, we have used a similar machine learning approach to achieve stateof-the-art NLI results. The goal of this paper is to demonstrate that our shallow and simple approach based on string kernels (with minor improvements) can pass the test of time and reach state-of-theart performance in the 2017 NLI shared task, despite the recent advances in natural language processing. We participated in all three tracks, in which the competitors were allowed to use only the essays (essay track), only the speech transcripts (speech track), or both (fusion track). Using only the data provided by the organizers for training our models, we have reached a macro F 1 score of 86.95% in the closed essay track, a macro F 1 score of 87.55% in the closed speech track, and a macro F 1 score of 93.19% in the closed * The authors have equally contributed to this work. fusion track. With these scores, our team (UnibucKernel) ranked in the first group of teams in all three tracks, while attaining the best scores in the speech and the fusion tracks.
doi:10.18653/v1/w17-5024 dblp:conf/bea/IonescuP17 fatcat:f4l43jwbvzastcfq7m3opnmc3u