DeepChannel: Salience Estimation by Contrastive Learning for Extractive Document Summarization

TL;DR

DeepChannel is a neural model for extractive summarization that estimates sentence salience using contrastive learning, achieving state-of-the-art results with high data efficiency and robustness across datasets.

Contribution

It introduces a contrastive training strategy for salience estimation, improving extractive summarization performance and data efficiency.

Findings

Achieves state-of-the-art ROUGE scores on CNN/Daily Mail.

Demonstrates robustness on out-of-domain DUC2007 dataset.

Reaches high ROUGE-1 F-1 with only 1% of training data.

Abstract

We propose DeepChannel, a robust, data-efficient, and interpretable neural model for extractive document summarization. Given any document-summary pair, we estimate a salience score, which is modeled using an attention-based deep neural network, to represent the salience degree of the summary for yielding the document. We devise a contrastive training strategy to learn the salience estimation network, and then use the learned salience score as a guide and iteratively extract the most salient sentences from the document as our generated summary. In experiments, our model not only achieves state-of-the-art ROUGE scores on CNN/Daily Mail dataset, but also shows strong robustness in the out-of-domain test on DUC2007 test set. Moreover, our model reaches a ROUGE-1 F-1 score of 39.41 on CNN/Daily Mail test set with merely $1 / 100$ training set, demonstrating a tremendous data efficiency.