New GRU from Convolutional Neural Network and Gated Recurrent Unit

被引：2

作者：

Atassi, A. ^{[1
]}

El Azami, I. ^{[1
]}

Sadiq, A. ^{[1
]}

机构：

[1] Univ Ibn Tofail, Fac Sci, Lab MISC, Kenitra, Morocco

来源：

PROCEEDINGS OF THE FIRST INTERNATIONAL CONFERENCE ON DATA SCIENCE, E-LEARNING AND INFORMATION SYSTEMS 2018 (DATA'18) | 2018年

关键词：

Convolutional Neural Network; CNN; Gated Recurrent Unit; GRU; SemEval; Twitter; word2vec; Keras; Adadelta; Adam; soft-max; deep learning;

D O I：

10.1145/3279996.3279998

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

This paper describes our comparison between two deep learning systems. Initially we start with the first system which is used Convolutional Neural Network CNN which we will compare with the second system which is used Gated Recurrent Unit GRU. And through this comparison is to propose a new system based on the positive points of the two previous systems and therefore this new system will take the right choice of hyper-parameters recommended by the authors of both systems. At the final stage we propose a method to apply this new system to the new Arabic language introduced in SemEval-2017.

引用

页数：2