Affiliation:
1. National University of Kyiv-Taras Shevchenko
2. National University of “Kyiv-Mohyla Academy”
Abstract
Cross language classification is an important task in multilingual learning, where documents in different languages often share the same set of categories. The main goal is to reduce the labeling cost of training classification model for each individual language. The novel approach by using Convolutional Neural Networks for multilingual language classification is proposed in this article. It learns representation of knowledge gained from languages. Moreover, current method works for new individual language, which was not used in training. The results of empirical study on large dataset of 21 languages demonstrate robustness and competitiveness of the presented approach.
Subject
General Physics and Astronomy,General Engineering
Reference26 articles.
1. Ko, Y., Seo, J. (2000). Automatic text categorization by unsupervised learning. Proceedings of the 18th Conference on Computational Linguistics, 1, 453–459. doi: 10.3115/990820.990886
2. Zhang, X., Le Cun, Y. (2016). Text Understanding from Scratch. arXiv:1502.01710v5 [cs.LG]. Available at: https://arxiv.org/pdf/1502.01710.pdf
3. Korde, V. (2012). Text Classification and Classifiers: A Survey. International Journal of Artificial Intelligence & Applications, 3 (2), 85–99. doi: 10.5121/ijaia.2012.3208
4. Schäuble, P. (1997). Multimedia Information Retrieval. Springer US, 138. doi: 10.1007/978-1-4615-6163-7
5. Krizhevsky, A., Sutskever, I., Hinton, G. E. (2012). ImageNet Classification with Deep Convolutional Neural Networks. Advances in Neural Information Processing Systems 25 (NIPS 2012), 1097–1105.
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献