Text classification with deep learning neural networks

P. 362–370.

Voronkov Ilia, Amajd M., Kaimuldenov Z.

In this paper, we analyze the use of different neural networks for the
text classification task. The accuracy of the studied text classifiers can be
changed by a small number of previously classified texts. This is important due
to the fact that in many applications of text classification a large number of un-
labeled texts are easily accessible, while the receipt of marked texts is quite a
difficult task. The paper also shows that the convolution neural network can
work better at the level of words, and does not require knowledge of the syntac-
tic or semantic structure of the language. On the other hand, a recurrent neural
network for the level of data representation in the form of a sequence can effec-
tively classify the text. Experimental results obtained for text corpora from two
different sources show that using a vector data representation can also improve
the accuracy of the classification.

Keywords: convolutional neural networks, text classification, word embeddings, recurrent neural network, Neural Network

In book

Actual Problems of System and Software Engineering 2017. Proceedings of the 5th International Conference on Actual Problems of System and Software Engineering Supported by Russian Foundation for Basic Research. Project #17-07-20565 Moscow, Russia, November 14-16, 2017, 408 P.

Vol. 1989. , Aachen: CEUR Workshop Proceedings, 2017.