Detecting economic events using a semantics-based pipeline

In today’s information-driven global economy, breaking news on economic events such as acquisitions and stock splits has a substantial impact on the financial markets. Therefore, it is important to be able to automatically identify events in news items accurately and in a timely manner. For this purpose, one has to be able to mine a wide variety of heterogeneous sources of unstructured data to extract knowledge that is useful for guiding decision making processes. We propose a Semanticsbased Pipeline for Economic Event Detection (SPEED), which aims at extracting financial events from news articles and annotating these events with meta-data, while retaining a speed that is high enough to make realtime use possible. In our pipeline implementation, we have reused some of the components of an existing framework and developed new ones, such as an Ontology Gazetteer and a Word Sense Disambiguator.