A word-building method based on neural network for text classification

Shuang, Kai, Guo, Hao, Zhang, Zhixuan, Loo, Jonathan ORCID: https://orcid.org/0000-0002-2197-8126 and Su, Sen (2019) A word-building method based on neural network for text classification. Journal of Experimental & Theoretical Artificial Intelligence, 31 (3). pp. 455-474. ISSN 0952-813X

[thumbnail of Loo_et_al_2019_A_word-building_method_based_on_neural_network_for_text_classification_.pdf]
Preview
PDF
Loo_et_al_2019_A_word-building_method_based_on_neural_network_for_text_classification_.pdf - Accepted Version

Download (2MB) | Preview

Abstract

Text classification is a foundational task in many natural language processing applications. All traditional text classifiers take words as the basic units and conduct the pre-training process (like word2vec) to directly generate word vectors at the first step. However, none of them have considered the information contained in word structure which is proved to be helpful for text classification. In this paper, we propose a word-building method based on neural network model that can decompose a Chinese word to a sequence of radicals and learn structure information from these radical level features which is a key difference from the existing models. Then, the convolutional neural network is applied to extract structure information of words from radical sequence to generate a word vector, and the long short-term memory is applied to generate the sentence vector for the prediction purpose. The experimental results show that our model outperforms other existing models on Chinese dataset. Our model is also applicable to English as well where an English word can be decomposed down to character level, which demonstrates the excellent generalisation ability of our model. The experimental results have proved that our model also outperforms others on English dataset.

Item Type: Article
Identifier: 10.1080/0952813X.2019.1572654
Additional Information: This is an Accepted Manuscript of an article published by Taylor & Francis in Journal of Experimental & Theoretical Artificial Intelligence on 30/01/2019, available online: http://www.tandfonline.com/10.1080/0952813X.2019.1572654.
Keywords: Convolutional neural network, long short term memory, structure information, text classification, word-building method
Subjects: Computing > Intelligent systems
Related URLs:
Depositing User: Users 4141 not found.
Date Deposited: 18 Feb 2019 17:29
Last Modified: 06 Feb 2024 15:59
URI: https://repository.uwl.ac.uk/id/eprint/5803

Downloads

Downloads per month over past year

Actions (login required)

View Item View Item

Menu