Multi-document Summarization by Graph Search and Matching

TL;DR

This paper introduces a novel graph-based method for multi-document summarization that captures similarities and differences by representing text as semantic graphs and matching them to generate natural language summaries.

Contribution

It presents a new approach combining graph representations and spreading activation for summarizing related documents, emphasizing semantic relations and differences.

Findings

Effective identification of semantic similarities and differences

Natural language summaries generated from graph matching

Evaluation shows promising results in summarization quality

Abstract

We describe a new method for summarizing similarities and differences in a pair of related documents using a graph representation for text. Concepts denoted by words, phrases, and proper names in the document are represented positionally as nodes in the graph along with edges corresponding to semantic relations between items. Given a perspective in terms of which the pair of documents is to be summarized, the algorithm first uses a spreading activation technique to discover, in each document, nodes semantically related to the topic. The activated graphs of each document are then matched to yield a graph corresponding to similarities and differences between the pair, which is rendered in natural language. An evaluation of these techniques has been carried out.