A word-building method based on neural network for text classification
- 13 December 2018
- journal article
- research article
- Published by Taylor & Francis in Journal of Experimental & Theoretical Artificial Intelligence
- Vol. 31 (3) , 455-474
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.Keywords
Funding Information
- National Key Research & Development Program of China (2016QY01W0200)
- Science and Technology on Communication Networks Laboratory (614210403070617)
This publication has 12 references indexed in Scilit:
- A rapid-prototyping framework for extracting small-scale incident-related information in microblogs: Application of multi-label classification on tweetsInformation Systems, 2016
- Inductive Model Generation for Text Classification Using a Bipartite Heterogeneous NetworkJournal of Computer Science and Technology, 2014
- Sentiment Analysis and Opinion MiningSynthesis Lectures on Human Language Technologies, 2012
- Neural Networks2012
- Opinion Mining and Sentiment AnalysisFoundations and Trends® in Information Retrieval, 2008
- Machine learning in automated text categorizationACM Computing Surveys, 2002
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Long Short-Term MemoryNeural Computation, 1997
- Learning long-term dependencies with gradient descent is difficultIEEE Transactions on Neural Networks, 1994
- Backpropagation Applied to Handwritten Zip Code RecognitionNeural Computation, 1989