Reinforced Abstractive Summarization with Adaptive Length Controlling

TL;DR

This paper introduces ALCO, a reinforcement learning-based method for controllable abstractive summarization that effectively manages length constraints while preserving salient information.

Contribution

ALCO is a novel two-stage summarization model that integrates length control and saliency estimation using reinforcement learning for improved content fidelity.

Findings

ALCO outperforms baseline methods in length controllability.

ALCO maintains higher content preservation.

ALCO demonstrates superior performance on CNN/Daily Mail dataset.

Abstract

Document summarization, as a fundamental task in natural language generation, aims to generate a short and coherent summary for a given document. Controllable summarization, especially of the length, is an important issue for some practical applications, especially how to trade-off the length constraint and information integrity. In this paper, we propose an \textbf{A}daptive \textbf{L}ength \textbf{C}ontrolling \textbf{O}ptimization (\textbf{ALCO}) method to leverage two-stage abstractive summarization model via reinforcement learning. ALCO incorporates length constraint into the stage of sentence extraction to penalize the overlength extracted sentences. Meanwhile, a saliency estimation mechanism is designed to preserve the salient information in the generated sentences. A series of experiments have been conducted on a wildly-used benchmark dataset \textit{CNN/Daily Mail}. The results have shown that ALCO performs better than the popular baselines in terms of length controllability and content preservation.