Two-Level Neural Network for Multi-label Document Classification
in 26th International Conference on Artificial Neural Networks (ICANN 2017) (2017)
Research topics:
Document ClassificationAbstract
This paper deals with multi-label document classification using neural networks. We propose a novel neural network which is composed of two sub-nets: the first one estimates the scores for all classes, while the second one determines the number of classes assigned to the document. The proposed approach is evaluated on Czech and English standard corpora. The experimental results show that the proposed method is competitive with state of the art on both languages.
Authors
BibTex
@inproceedings{lenckral2017icann, title = {Two-Level Neural Network for Multi-label Document Classification}, author = {Lenc, Ladislav and Kr{\'a}l, Pavel}, booktitle = {in 26th International Conference on Artificial Neural Networks (ICANN 2017)}, pages = {368-375}, month = {11-14 September}, year = {2017}, address = {Alghero, Sardinia, Italy}, publisher = {Springer}, isbn = {978-3-319-68611-0}, doi = {10.1007/978-3-319-68612-7_42} }
