An Introduction to the Summarization of Evolving Events: Linear and Non-linear Evolution

TL;DR

This paper explores methods for summarizing evolving events over time, considering different types of event evolution and source reports, and proposes a multi-document summarization approach using message representations and cross-document relations.

Contribution

It introduces a novel multi-document summarization approach for evolving events using message-based representations and cross-document relations, with an implemented system prototype.

Findings

Proposes a message-based approach for event summarization

Defines cross-document relations for incident linking

Develops a summarization system prototype

Abstract

This paper examines the summarization of events that evolve through time. It discusses different types of evolution taking into account the time in which the incidents of an event are happening and the different sources reporting on the specific event. It proposes an approach for multi-document summarization which employs ``messages'' for representing the incidents of an event and cross-document relations that hold between messages according to certain conditions. The paper also outlines the current version of the summarization system we are implementing to realize this approach.