Multi-layered graph-based multi-document summarization model
This work addresses the problem of generating summaries from multiple documents for users needing concise information, but it appears incremental by building on existing graph-based methods.
The paper tackles multi-document summarization by proposing a novel 3-layered graph model that incorporates under-sentence level relations, such as part-of-sentence similarity, to improve extractive summarization, though no concrete performance numbers are provided in the abstract.
Multi-document summarization is a process of automatic generation of a compressed version of the given collection of documents. Recently, the graph-based models and ranking algorithms have been actively investigated by the extractive document summarization community. While most work to date focuses on homogeneous connecteness of sentences and heterogeneous connecteness of documents and sentences (e.g. sentence similarity weighted by document importance), in this paper we present a novel 3-layered graph model that emphasizes not only sentence and document level relations but also the influence of under sentence level relations (e.g. a part of sentence similarity).