Learning Semantically Coherent and Reusable Kernels in Convolution Neural Nets for Sentence Classification
arXiv: Computation and Language, Volume abs/1608.00466, 2016.
The state-of-the-art CNN models give good performance on sentence classification tasks. The purpose of this work is to empirically study desirable properties such as semantic coherence, attention mechanism and reusability of CNNs in these tasks. Semantically coherent kernels are preferable as they are a lot more interpretable for explaini...More
PPT (Upload PPT)