Research on Tibetan Text Classification Method Based on Neural Network
Authors:
- 1 November 2019
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 379-383
Abstract
Text categorization is an important task in natural language processing, and it has a wide range of applications in real life. In this paper, two N-Gram feature models (MLP, FastText) and two sequential models (sepCNN, Bi-LSTM) are used to study the automatic classification for Tibetan text based on syllables and vocabulary. The experiment on Tibetan language data collected by China Tibet News Network shows that the classification accuracy is about 85%.Keywords
This publication has 10 references indexed in Scilit:
- Comparing automated text classification methodsInternational Journal of Research in Marketing, 2019
- Xception: Deep Learning with Depthwise Separable Convolutions2017
- Intellectual Approaches to Improvement of the Classification Decisions Quality on the Base of the SVM ClassifierProcedia Computer Science, 2017
- A comparative performance evaluation of neural network based approach for sentiment classification of online reviewsJournal of King Saud University Computer and Information Sciences, 2016
- Convolutional Neural Networks for Sentence Classification2014
- KNN with TF-IDF based Framework for Text CategorizationProcedia Engineering, 2014
- Incorporating logistic regression to decision-theoretic rough sets for classificationsInternational Journal of Approximate Reasoning, 2014
- Rule-based text categorization using hierarchical categories2002
- Bidirectional recurrent neural networksIEEE Transactions on Signal Processing, 1997
- On Relevance, Probabilistic Indexing and Information RetrievalJournal of the ACM, 1960