Many real–world information needs are naturally formulated as queries with temporal constraints. However, the structured temporal background information needed to support such constraints is usually not available to information retrieval systems. As an alternative, we automatically compile temporal knowledge bases from web documents, combining whatever quantitative and qualitative temporal information we can find about events of interest. By using simple heuristic techniques for temporal information extraction, we initially focus more on recall than on precision, relying on the subsequent application of a fuzzy temporal reasoner to improve the reliability of the extracted information.
Steven Schockaert, Martine De Cock, Etienne E. Ker