Classify or Select: Neural Architectures for Extractive Document Summarization

TL;DR

This paper introduces two novel RNN-based architectures for extractive document summarization, one sequential and one flexible, demonstrating their effectiveness and interpretability through experimental evaluation.

Contribution

The paper proposes two contrasting RNN architectures for extractive summarization, highlighting their interpretability and comparative performance on multiple datasets.

Findings

Models reach or outperform state-of-the-art results

Sequential and flexible architectures have different strengths

Interpretability through visualization of features

Abstract

We present two novel and contrasting Recurrent Neural Network (RNN) based architectures for extractive summarization of documents. The Classifier based architecture sequentially accepts or rejects each sentence in the original document order for its membership in the final summary. The Selector architecture, on the other hand, is free to pick one sentence at a time in any arbitrary order to piece together the summary. Our models under both architectures jointly capture the notions of salience and redundancy of sentences. In addition, these models have the advantage of being very interpretable, since they allow visualization of their predictions broken up by abstract features such as information content, salience and redundancy. We show that our models reach or outperform state-of-the-art supervised models on two different corpora. We also recommend the conditions under which one architecture is superior to the other based on experimental evidence.