AREDSUM: Adaptive Redundancy-Aware Iterative Sentence Ranking for Extractive Document Summarization

TL;DR

This paper introduces two adaptive models for extractive summarization that explicitly model redundancy and salience, demonstrating improved performance over existing methods on benchmark datasets.

Contribution

It presents novel adaptive learning models, AREDSUM-SEQ and AREDSUM-CTX, that separately and jointly consider salience and redundancy for better extractive summarization.

Findings

AREDSUM-CTX outperforms state-of-the-art baselines.

Modeling diversity explicitly improves summary quality.

Two-step approach effectively measures salience and redundancy impact.

Abstract

Redundancy-aware extractive summarization systems score the redundancy of the sentences to be included in a summary either jointly with their salience information or separately as an additional sentence scoring step. Previous work shows the efficacy of jointly scoring and selecting sentences with neural sequence generation models. It is, however, not well-understood if the gain is due to better encoding techniques or better redundancy reduction approaches. Similarly, the contribution of salience versus diversity components on the created summary is not studied well. Building on the state-of-the-art encoding methods for summarization, we present two adaptive learning models: AREDSUM-SEQ that jointly considers salience and novelty during sentence selection; and a two-step AREDSUM-CTX that scores salience first, then learns to balance salience and redundancy, enabling the measurement of the impact of each aspect. Empirical results on CNN/DailyMail and NYT50 datasets show that by modeling diversity explicitly in a separate step, AREDSUM-CTX achieves significantly better performance than AREDSUM-SEQ as well as state-of-the-art extractive summarization baselines.