English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The state-of-the-art CNN models give good performance on sentenceclassification tasks. The purpose of this work is to empirically studydesirable properties such as semantic coherence, attention mechanism andreusability of CNNs in these tasks. Semantically coherent kernels arepreferable as they are a lot more interpretable for explaining the decision ofthe learned CNN model. We observe that the learned kernels do not have semanticcoherence. Motivated by this observation, we propose to learn kernels withsemantic coherence using clustering scheme combined with Word2Vecrepresentation and domain knowledge such as SentiWordNet. We suggest atechnique to visualize attention mechanism of CNNs for decision explanationpurpose. Reusable property enables kernels learned on one problem to be used inanother problem. This helps in efficient learning as only a few additionaldomain specific filters may have to be learned. We demonstrate the efficacy ofour core ideas of learning semantically coherent kernels and leveragingreusable kernels for efficient learning on several benchmark datasets.Experimental results show the usefulness of our approach by achievingperformance close to the state-of-the-art methods but with semantic andreusable properties.

Learning Semantically Coherent and Reusable Kernels in Convolution Neural Nets for Sentence Classification