UnibucKernel Reloaded: First Place in Arabic Dialect Identification for the Second Year in a Row

Andrei Butnaru, Radu Tudor Ionescu


Abstract
We present a machine learning approach that ranked on the first place in the Arabic Dialect Identification (ADI) Closed Shared Tasks of the 2018 VarDial Evaluation Campaign. 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 speech or phonetic transcripts, we also use a kernel based on dialectal embeddings generated from audio recordings by the organizers. In the learning stage, we independently employ Kernel Discriminant Analysis (KDA) and Kernel Ridge Regression (KRR). Preliminary experiments indicate that KRR provides better classification results. Our approach is shallow and simple, but the empirical results obtained in the 2018 ADI Closed Shared Task prove that it achieves the best performance. Furthermore, our top macro-F1 score (58.92%) is significantly better than the second best score (57.59%) in the 2018 ADI Shared Task, according to the statistical significance test performed by the organizers. Nevertheless, we obtain even better post-competition results (a macro-F1 score of 62.28%) using the audio embeddings released by the organizers after the competition. With a very similar approach (that did not include phonetic features), we also ranked first in the ADI Closed Shared Tasks of the 2017 VarDial Evaluation Campaign, surpassing the second best method by 4.62%. We therefore conclude that our multiple kernel learning method is the best approach to date for Arabic dialect identification.
Anthology ID:
W18-3909
Volume:
Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018)
Month:
August
Year:
2018
Address:
Santa Fe, New Mexico, USA
Editors:
Marcos Zampieri, Preslav Nakov, Nikola Ljubešić, Jörg Tiedemann, Shervin Malmasi, Ahmed Ali
Venue:
VarDial
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
77–87
Language:
URL:
https://aclanthology.org/W18-3909
DOI:
Bibkey:
Cite (ACL):
Andrei Butnaru and Radu Tudor Ionescu. 2018. UnibucKernel Reloaded: First Place in Arabic Dialect Identification for the Second Year in a Row. In Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018), pages 77–87, Santa Fe, New Mexico, USA. Association for Computational Linguistics.
Cite (Informal):
UnibucKernel Reloaded: First Place in Arabic Dialect Identification for the Second Year in a Row (Butnaru & Ionescu, VarDial 2018)
Copy Citation:
PDF:
https://aclanthology.org/W18-3909.pdf