Text Classification Using Parallel Word-level and Character-level Embeddings in Convolutional Neural Networks
Autor: | Jungyeon Jang, Jong Woo Kim, Juwon Lee, Kim Ki Tae, Geonu Kim, Woonyoung Yeo |
---|---|
Rok vydání: | 2019 |
Předmět: |
Information Systems and Management
Word embedding Sociology and Political Science business.industry Computer science Deep learning Pattern recognition 010501 environmental sciences 01 natural sciences Convolutional neural network Support vector machine 03 medical and health sciences Naive Bayes classifier 0302 clinical medicine Recurrent neural network Embedding 030212 general & internal medicine Artificial intelligence business Word (computer architecture) 0105 earth and related environmental sciences |
Zdroj: | Asia Pacific Journal of Information Systems. 29:771-788 |
ISSN: | 2288-6818 2288-5404 |
DOI: | 10.14329/apjis.2019.29.4.771 |
Popis: | Deep learning techniques such as Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) show superior performance in text classification than traditional approaches such as Support Vector Machines (SVMs) and Naive Bayesian approaches. When using CNNs for text classification tasks, word embedding or character embedding is a step to transform words or characters to fixed size vectors before feeding them into convolutional layers. In this paper, we propose a parallel word-level and character-level embedding approach in CNNs for text classification. The proposed approach can capture word-level and character-level patterns concurrently in CNNs. To show the usefulness of proposed approach, we perform experiments with two English and three Korean text datasets. The experimental results show that character-level embedding works better in Korean and word-level embedding performs well in English. Also the experimental results reveal that the proposed approach provides better performance than traditional CNNs with word-level embedding or character-level embedding in both Korean and English documents. From more detail investigation, we find that the proposed approach tends to perform better when there is relatively small amount of data comparing to the traditional embedding approaches. |
Databáze: | OpenAIRE |
Externí odkaz: |