Earticle

초록

영어

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 Naïve 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.

목차

ABSTRACT
Ⅰ. Introduction
Ⅱ. Related Work
2.1. Text Classification
2.2. Deep Learning in Text Mining
2.3. Convolutional Neural Networks (CNNs) for Text Classification
Ⅲ. Proposed Approach
3.1. Hyperparameters Configuration
3.2. Word Vector and Character Vector
3.3. Regularization and Normalization
Ⅳ. Experimental Design and Datasets
4.1. Comparing Models
4.2. Datasets
Ⅴ. Results and Discussion
5.1. Comlementary Effect
5.2. Size Effect
5.3. Possibility of Improvement through Hyperparameter and Embedding optimization
5.4. Implications
Ⅵ. Conclusion and Future Work
Acknowledgements

키워드

저자

• Geonu Kim [ Undergraduate Student, School of Business, Hanyang University, Korea ]
• Jungyeon Jang [ Manager, Hyundai Motor Company, Korea ]
• Juwon Lee [ Analyst, Korea Ratings, Korea ]
• Kitae Kim [ Researcher, Hana Institute of Finance, KEB Hana Bank, Korea ]
• Woonyoung Yeo [ M.S. Student, Business Informatics from Graduate School, Hanyang University, Korea ]
• Jong Woo Kim [ Professor, School of Business, Hanyang University, Korea ] Corresponding author

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  Asia Pacific Journal of Information Systems

• 간기

  계간

• pISSN

  2288-5404

• eISSN

  2288-6818

• 수록기간

  1990~2026

• 등재여부

  KCI 등재,SCOPUS

• 십진분류

  KDC 325 DDC 658