Reinforced Abstractive Summarization with Adaptive Length Controlling
This work addresses a practical issue in document summarization for applications requiring controlled summary lengths, though it is incremental as it builds on existing two-stage abstractive summarization models.
The paper tackles the problem of generating summaries with specific length constraints while preserving information integrity, proposing an adaptive length controlling optimization method that outperforms popular baselines on the CNN/Daily Mail dataset in terms of length controllability and content preservation.
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.