TY - GEN
T1 - A Hybrid Algorithm for Text Classification Based on CNN-BLSTM with Attention
AU - Fu, Lei
AU - Yin, Zhao Xia
AU - Wang, Xin
AU - Liu, Yi
N1 - Publisher Copyright:
© 2018 IEEE.
PY - 2018/7/2
Y1 - 2018/7/2
N2 - We propose an effective text classification framework, which is the hybrid of different weights of character-level and word-level features through concatenation based on Convolutional Neural Network-bidirectional long short-term memory with attention (BACNN). The first step is word segmentation or character segmentation in the process of Chinese natural language processing. However, due to the different semantic relations in Chinese, Chinese sentences usually have several ways of word segmentation, which leads to the problem of word segmentation ambiguity. Although Chinese character segmentation is not ambiguity, its meaning is not accurate and rich enough. And in different situations, the character and word are different in importance. Therefore, to overcome the above problems, we propose the method of hybrid different weights of word-level and character-level features to let them make up the respective shortcomings. The experiment results indicate that our proposed method is better than the simple word or character level feature in classification performance.
AB - We propose an effective text classification framework, which is the hybrid of different weights of character-level and word-level features through concatenation based on Convolutional Neural Network-bidirectional long short-term memory with attention (BACNN). The first step is word segmentation or character segmentation in the process of Chinese natural language processing. However, due to the different semantic relations in Chinese, Chinese sentences usually have several ways of word segmentation, which leads to the problem of word segmentation ambiguity. Although Chinese character segmentation is not ambiguity, its meaning is not accurate and rich enough. And in different situations, the character and word are different in importance. Therefore, to overcome the above problems, we propose the method of hybrid different weights of word-level and character-level features to let them make up the respective shortcomings. The experiment results indicate that our proposed method is better than the simple word or character level feature in classification performance.
KW - Attention mechanism
KW - Bidirectional long short-term memory
KW - Convolutional Neural Network
KW - Text classification
UR - https://www.scopus.com/pages/publications/85062785864
U2 - 10.1109/IALP.2018.8629219
DO - 10.1109/IALP.2018.8629219
M3 - 会议稿件
AN - SCOPUS:85062785864
T3 - Proceedings of the 2018 International Conference on Asian Language Processing, IALP 2018
SP - 31
EP - 34
BT - Proceedings of the 2018 International Conference on Asian Language Processing, IALP 2018
A2 - Dong, Minghui
A2 - Bijaksana, Moch.
A2 - Sujaini, Herry
A2 - Negara, Arif Bijaksana Putra
A2 - Romadhony, Ade
A2 - Ruskanda, Fariska Z.
A2 - Nurfadhilah, Elvira
A2 - Aini, Lyla Ruslana
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 22nd International Conference on Asian Language Processing, IALP 2018
Y2 - 15 November 2018 through 17 November 2018
ER -