Neural Summarization by Extracting Sentences and Words

TL;DR

This paper introduces a neural network-based extractive summarization method that uses a hierarchical encoder and attention mechanism, achieving state-of-the-art results without linguistic features.

Contribution

It presents a flexible, data-driven framework for extractive summarization that can extract sentences or words using neural networks, bypassing traditional feature engineering.

Findings

Achieves results comparable to state-of-the-art methods

Operates without linguistic annotation

Works on large-scale datasets

Abstract

Traditional approaches to extractive summarization rely heavily on human-engineered features. In this work we propose a data-driven approach based on neural networks and continuous sentence features. We develop a general framework for single-document summarization composed of a hierarchical document encoder and an attention-based extractor. This architecture allows us to develop different classes of summarization models which can extract sentences or words. We train our models on large scale corpora containing hundreds of thousands of document-summary pairs. Experimental results on two summarization datasets demonstrate that our models obtain results comparable to the state of the art without any access to linguistic annotation.