Hierarchical Attention Networks for Document ClassificationEI
HLT-NAACL, pp. 1480-1489, 2016.
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...More