Unsupervised Dual-Cascade Learning with Pseudo-Feedback Distillation for Query-based Extractive Summarization
This addresses the problem of generating focused and salient summaries from multiple documents for users needing efficient information retrieval, representing a notable advance over existing methods.
The paper tackled the tradeoff between saliency and focus in query-based extractive summarization by proposing Dual-CES, an unsupervised method that significantly outperformed all other state-of-the-art unsupervised alternatives and even outperformed strong supervised summarizers.
We propose Dual-CES -- a novel unsupervised, query-focused, multi-document extractive summarizer. Dual-CES is designed to better handle the tradeoff between saliency and focus in summarization. To this end, Dual-CES employs a two-step dual-cascade optimization approach with saliency-based pseudo-feedback distillation. Overall, Dual-CES significantly outperforms all other state-of-the-art unsupervised alternatives. Dual-CES is even shown to be able to outperform strong supervised summarizers.