• DOI:10.18653/v1/N16-1174
Corpus ID: 6857205

Hierarchical Attention Networks for Document Classification

@inproceedings{Yang2016HierarchicalAN,
  title={Hierarchical Attention Networks for Document Classification},
  author={Zichao Yang and Diyi Yang and Chris Dyer and X. He and Alex Smola and E. Hovy},
  booktitle={HLT-NAACL},
  year={2016}
}

• Zichao Yang, Diyi Yang, +3 authors E. Hovy
• Published in HLT-NAACL 2016
• Computer Science

We propose a hierarchical attention network for document classification. Our model has two distinctive characteristics: (i) it has a hierarchical structure that mirrors the hierarchical structure of documents; (ii) it has two levels of attention mechanisms applied at the wordand sentence-level, enabling it to attend differentially to more and less important content when constructing the document representation. Experiments conducted on six large scale text classification tasks demonstrate that… Expand

View on ACL

cs.cmu.edu

Save to Library

Create Alert

Cite

Launch Research Feed