Turkish Tweet Classification with Transformer Encoder

Atıf Emre Yüksel, Yaşar Alim Türkmen, Arzucan Özgür, Berna Altınel


Abstract
Short-text classification is a challenging task, due to the sparsity and high dimensionality of the feature space. In this study, we aim to analyze and classify Turkish tweets based on their topics. Social media jargon and the agglutinative structure of the Turkish language makes this classification task even harder. As far as we know, this is the first study that uses a Transformer Encoder for short text classification in Turkish. The model is trained in a weakly supervised manner, where the training data set has been labeled automatically. Our results on the test set, which has been manually labeled, show that performing morphological analysis improves the classification performance of the traditional machine learning algorithms Random Forest, Naive Bayes, and Support Vector Machines. Still, the proposed approach achieves an F-score of 89.3 % outperforming those algorithms by at least 5 points.
Anthology ID:
R19-1158
Volume:
Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019)
Month:
September
Year:
2019
Address:
Varna, Bulgaria
Editors:
Ruslan Mitkov, Galia Angelova
Venue:
RANLP
SIG:
Publisher:
INCOMA Ltd.
Note:
Pages:
1380–1387
Language:
URL:
https://aclanthology.org/R19-1158
DOI:
10.26615/978-954-452-056-4_158
Bibkey:
Cite (ACL):
Atıf Emre Yüksel, Yaşar Alim Türkmen, Arzucan Özgür, and Berna Altınel. 2019. Turkish Tweet Classification with Transformer Encoder. In Proceedings of the International Conference on Recent Advances in Natural Language Processing (RANLP 2019), pages 1380–1387, Varna, Bulgaria. INCOMA Ltd..
Cite (Informal):
Turkish Tweet Classification with Transformer Encoder (Yüksel et al., RANLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/R19-1158.pdf