Interpretation Support System for Classification Patterns Using HMM in Deep Learning with Texts

• Published in: Journal of Japan Society for Fuzzy Theory and Intelligent Informatics Vol. 34; no. 1; pp. 501 - 510
• Main Authors: ANDO, Masayuki, KAWAHARA, Yoshinobu, SUNAYAMA, Wataru, HATANAKA, Yuji
• Format: Journal Article
• Language: English
• Published: Iizuka Japan Society for Fuzzy Theory and Intelligent Informatics 15.02.2022; Japan Science and Technology Agency
• Subjects: Classification; data visualization; Deep learning; Displays; interpretation support; Machine learning; Sentences; Support systems; text classification; text mining; Texts
• ISSN: 1347-7986; 1881-7203
• DOI: 10.3156/jsoft.34.1_501

This paper describes an interpretation support system for classification patterns extracted from deep learning with texts using HMM, and verified its effectiveness. It is well known that classification patterns by deep learning models are often difficult to interpret the reasons derived. In the proposed system, the content of deep learning results is extracted using HMMs, and classification patterns are provided for the system users to interpret the learned features. Then, the system displays learned network structures so that anyone can easily understand learning results. In verification experiments to confirm the effectiveness of the system, based on the learning result of deep learning classifying sentences, in the experiment, the subjects were divided into two groups. One group used the proposed system. The other group used the system that displays words with high TFIDF values. The both groups were instructed to give meanings of classification patterns peculiar to each output. The results show that the subjects who used the proposed system were able to understand the meanings of the classification patterns of deep learning with texts more deeply than those who used the comparison system.