A Sentence Compression Based Framework to Query-Focused Multi-Document Summarization
This work addresses the problem of generating concise, query-relevant summaries from multiple documents, which is incremental as it builds on existing sentence compression techniques.
The paper tackles query-focused multi-document summarization by developing a sentence compression framework with learning-based models and an innovative beam search decoder, achieving statistically significant improvements such as 8.0% and 5.4% in ROUGE-2 on DUC 2006 and 2007 tasks.
We consider the problem of using sentence compression techniques to facilitate query-focused multi-document summarization. We present a sentence-compression-based framework for the task, and design a series of learning-based compression models built on parse trees. An innovative beam search decoder is proposed to efficiently find highly probable compressions. Under this framework, we show how to integrate various indicative metrics such as linguistic motivation and query relevance into the compression process by deriving a novel formulation of a compression scoring function. Our best model achieves statistically significant improvement over the state-of-the-art systems on several metrics (e.g. 8.0% and 5.4% improvements in ROUGE-2 respectively) for the DUC 2006 and 2007 summarization task.