Open AccessResearch on the Performance of Character Convolutional Neural Network in Different Text Encoding Formats
Author(s) -
Zhiyao Bao
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1748/3/032003
Subject(s) - convolutional neural network , computer science , character (mathematics) , artificial intelligence , deep learning , task (project management) , encoding (memory) , feature (linguistics) , field (mathematics) , natural language processing , artificial neural network , linguistics , engineering , philosophy , geometry , mathematics , systems engineering , pure mathematics
With the continuous progress and development of society, text classification has become an important task in the field of text data mining and text value exploration. Compared with existing text classification technology, deep learning technology has many advantages, such as high accuracy and effective feature extraction. This paper is mainly based on the character convolutional neural network to study the classification performance of different texts, hoping to provide experience for related research work. Through research, it is found that character-level convolutional neural network deep learning technology can achieve Chinese text classification more effectively.