Group sparse CNNs for question classification with answer sets
Mingbo Ma, Liang Huang, et al.
ACL 2017
In a multi-label text classification task, in which multiple labels can be assigned to one text, label co-occurrence itself is informative. We propose a novel neural network initialization method to treat some of the neurons in the final hidden layer as dedicated neurons for each pattern of label co-occurrence. These dedicated neurons are initialized to connect to the corresponding co-occurring labels with stronger weights than to others. In experiments with a natural language query classification task, which requires multi-label classification, our initialization method improved classification accuracy without any computational overhead in training and evaluation.
Mingbo Ma, Liang Huang, et al.
ACL 2017
Bowen Zhou, Bing Xiang, et al.
SSST 2008
Mo Yu, Wenpeng Yin, et al.
ACL 2017
Jia Cui, Yonggang Deng, et al.
ASRU 2009