News text classification based on multi-head attention and parallel capsule networks

Dong Wang; Panpan Peng

doi:10.1117/12.2659349

30 November 2022 News text classification based on multi-head attention and parallel capsule networks

Dong Wang, Panpan Peng

Proceedings Volume 12456, International Conference on Artificial Intelligence and Intelligent Information Processing (AIIIP 2022); 124561N (2022) https://doi.org/10.1117/12.2659349
Event: International Conference on Artificial Intelligence and Intelligent Information Processing (AIIIP 2022), 2022, Qingdao, China

Abstract

The recognition effect of news text sequence data is strongly related to the importance of each word and the dependency relationship between them. Although the capsule network can learn the correlation information between news text as a whole and local, it lacks the attention to the key words in the text and ignores the distant dependencies in the text. To remedy the above shortcomings, this paper proposes a news text classification model which is based on multi-head attention and parallel capsule networks, using a multi-head attention layer for feature extraction and then a parallel capsule network module as the classification layer. The model can retrieve wealthier text details. Experimental results demonstrate that the proposed model of this paper works better than the mainstream capsule network based text classification models in both single-label and multi-label classification tasks of news texts.

Citation Download Citation

Dong Wang and Panpan Peng "News text classification based on multi-head attention and parallel capsule networks", Proc. SPIE 12456, International Conference on Artificial Intelligence and Intelligent Information Processing (AIIIP 2022), 124561N (30 November 2022); https://doi.org/10.1117/12.2659349

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available