The electronics newspaper becomes a main source for online news readers. When facing the numerous stories, news readers need some supports in order to review a topic in short time. Due to previous researches in TDT (Topic Detection and Tracking) only considering how to identify events and present the results with news titles and keywords, a summarized text to present event evolution is necessary for general news readers to retrospect events under a news topic. This thesis proposes a topic retrospection process and implements the SToRe system that identifies various events under a new topic and constructs the relationship to compose a summary which gives readers the sketch of event evolution in a topic. It consists of three main functions: event identification, main storyline construction and storyline-based summarization. The constructed main storyline can remove the irrelevant events and present a main theme. The summarization extracts the representative sentences and takes the main theme as the template to compose summary. The summarization not only provides enough information to comprehend the development of a topic, but also can be an index to help readers to find more detailed information. A lab experiment is conducted to evaluate the SToRe system in the question-and-answer (Q&A) setting. From the experimental results, the SToRe system can help news readers more effectively and efficiently to capture the development of a topic.

Esta tesis intenta demostrar cómo los sistemas de Recuperación de Información (RI) y los sistemas de Detección de Sucesos (TDT - Topic Detection and Tracking) mejoran si se añade una componente temporal extraída automáticamente del texto, a la cual denominaremos periodo de suceso. Este atributo representa el espacio de tiempo en el que transcurre el suceso principal relatado en cada documento. Con este propósito la tesis ha cubierto los siguientes objetivos: * Definición de un modelo de tiempo para representar y manipular las referencias temporales que aparecen en un texto. * Desarrollo de una aplicación para la extracción de expresiones temporales lingüísticas y el reconocimiento del intervalo absoluto que referencian según el calendario Gregoriano. * Implementación de un sistema para la extracción automática del periodo de suceso. * Modificación de los actuales sistemas de RI, TDT para incluir la información temporal extraída con las herramientas anteriores.