Multi-layered graph-based multi-document summarization model

TL;DR

This paper introduces a novel three-layered graph model for multi-document summarization that captures sentence, document, and sub-sentence relations to improve extractive summarization quality.

Contribution

The paper proposes a new multi-layered graph model that incorporates sub-sentence level relations, enhancing the representation of document structures for summarization.

Findings

Enhanced summarization performance demonstrated

Effective modeling of sub-sentence relations

Improved ranking accuracy in summarization

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).