Hybrid MemNet for Extractive Summarization
This work addresses the problem of single document summarization for natural language processing applications, offering a data-driven approach that improves upon existing methods.
The authors tackled extractive text summarization by proposing a fully data-driven end-to-end deep network called Hybrid MemNet, which learns continuous unified document representations and jointly captures local and global sentential information, resulting in significant performance gains on two corpora compared to state-of-the-art baselines.
Extractive text summarization has been an extensive research problem in the field of natural language understanding. While the conventional approaches rely mostly on manually compiled features to generate the summary, few attempts 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. The network learns the continuous unified 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 different corpora confirm that our model shows significant performance gains compared with the state-of-the-art baselines.