Unity in Diversity: Learning Distributed Heterogeneous Sentence Representation for Extractive Summarization

TL;DR

This paper introduces HNet, a novel data-driven system for extractive multi-document summarization that learns sentence representations capturing semantic and compositional features, leading to improved performance over traditional methods.

Contribution

The paper presents HNet, a new neural network model that learns document-independent sentence features for extractive summarization, outperforming existing approaches on benchmark datasets.

Findings

Achieved 1.5-2 ROUGE points improvement over baselines.

Effectively captures semantic and compositional sentence features.

Demonstrates robustness across multiple DUC datasets.

Abstract

Automated multi-document extractive text summarization is a widely studied research problem in the field of natural language understanding. Such extractive mechanisms compute in some form the worthiness of a sentence to be included into the summary. While the conventional approaches rely on human crafted document-independent features to generate a summary, we develop a data-driven novel summary system called HNet, which exploits the various semantic and compositional aspects latent in a sentence to capture document independent features. The network learns sentence representation in a way that, salient sentences are closer in the vector space than non-salient sentences. This semantic and compositional feature vector is then concatenated with the document-dependent features for sentence ranking. Experiments on the DUC benchmark datasets (DUC-2001, DUC-2002 and DUC-2004) indicate that our model shows significant performance gain of around 1.5-2 points in terms of ROUGE score compared with the state-of-the-art baselines.