A survey of text classification: problem statement, latest methods and popular datasets-Reference-Cited by-同舟云学术

A survey of text classification: problem statement, latest methods and popular datasets

Published:2022-08-03 Issue: Volume:7 Page:357-367
ISSN:2791-0210
Container-title:Highlights in Science, Engineering and Technology
language:
Short-container-title:HSET

Author:

Tian Siyu,Huang Xinyao

Abstract

Considering the important role text classification plays in natural language processing tasks, improving the accuracy and efficiency of text classification has been a priority in recent work. In this paper, we focus on the latest text classification methods and sort them into three categories: embedding methods, language models, and various neural networks. We summarize the state of current research and the insufficiencies which may be directions for future study.

Publisher

Darcy & Roy Press Co. Ltd.

Reference46 articles.

1. Abreu, J., Fred, L., Macêdo, D., & Zanchettin, C. (2019). Hierarchical Attentional Hybrid Neural Networks for Document Classification. https://doi.org/10.1007/978-3-030-30493-5_39.

2. Adhikari, A., Ram, A., Tang, R., & Lin, J. (2019). DocBERT: BERT for Document Classification. http://arxiv.org/abs/1904.08398.

3. Adhikari, A., Ram, A., Tang, R., Lin, J., & Cheriton, D. R. (2019). Rethinking Complex Neural Network Architectures for Document Classification (pp. 4046–4051). https://github.com/lancopku/SGM.

4. Benballa, M., Collet, S., & Picot-Clemente, R. (2020). Saagie at Semeval-2019 Task 5: From Universal Text Embeddings and Classical Features to Domain-specific Text Classification (pp. 469–475). https://github.com/shivam5992/.

5. Chang, W. C., Yu, H. F., Zhong, K., Yang, Y., & Dhillon, I. S. (2020). Taming Pretrained Transformers for Extreme Multi-label Text Classification. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 3163–3171. https://doi.org/10.1145/3394486.3403368.