Hybrid MemNet for Extractive Summarization

Abhishek Singh, Manish Gupta, Vasudeva Varma

Abstract:

Extractive text summarization has been an extensive research problem in the €eld of natural language understanding. While the
conventional approaches rely mostly on manually compiled features to generate the summary, few aŠempts have been made in
developing data-driven systems for extractive summarization. To
this end, we present a fully data-driven end-to-end deep network
which we call as Hybrid MemNet for single document summarization task. Œe network learns the continuous uni€ed representation
of a document before generating its summary. It jointly captures
local and global sentential information along with the notion of
summary worthy sentences. Experimental results on two di‚erent
corpora con€rm that our model shows signi€cant performance
gains compared with the state-of-the-art baselines