Long Document Classification From Local Word Glimpses via Recurrent Attention Learning

Long Document Classification From Local Word Glimpses via Recurrent Attention Learning

Document classification requires to extract high-level features from low-level word vectors. Typically, feature extraction by deep neural networks makes use of all words in a document, which cannot scale well for a long document. In this paper, we propose to tackle the long document classification t...

Full description

Bibliographic Details
Main Authors: Jun He, Liqun Wang, Liu Liu, Jiao Feng, Hao Wu
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Document classification
deep learning
reinforcement learning
recurrent attention learning
Online Access:https://ieeexplore.ieee.org/document/8675939/

Internet

https://ieeexplore.ieee.org/document/8675939/

Similar Items