2011 | OriginalPaper | Buchkapitel
Online News Event Extraction for Global Crisis Surveillance
verfasst von : Jakub Piskorski, Hristo Tanev, Martin Atkinson, Eric van der Goot, Vanni Zavarella
Erschienen in: Transactions on Computational Collective Intelligence V
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
This article presents a real-time and multilingual news event extraction system developed at the Joint Research Centre of the European Commission. It is capable of accurately and efficiently extracting violent and natural disaster events from online news. In particular, a linguistically relatively lightweight approach is deployed, in which clustered news are heavily exploited at all stages of processing. Furthermore, the technique applied for event extraction assumes the inverted-pyramid style of writing news articles, i.e., the most important parts of the story are placed in the beginning and the least important facts are left toward the end. The article focuses on the system’s architecture, real-time news clustering, geo-locating and geocoding clusters, event extraction grammar development, adapting the system to the processing of new languages, cluster-level information fusion, visual event tracking, event extraction accuracy evaluation, and detecting event reporting boundaries in news article streams. This article is an extended version of [20].