Historical Timeline Mining And Extraction

The acronym HiTiME stands for Historical Timeline Mining and Extraction. HiTiME aims at the development of a text analysis system for the recognition and extraction of historical events and facts. Both primary and secondary historical sources are used, such as biographies, brochures, letters and newspapers. To this end, HiTiME exploits a combination of text and data mining technologies, so as to convert a heterogeneous collection of text sources into a “historical web of knowledge”. More specifically, an associative network of historically relevant entities and their relations, linked to a timeline. Consequently, this network is browsable and searchable using both conventional keyword queries, as well as visual interfaces, such as timelines, maps and network viewers.

HiTiME is part of NWO‘s CATCH programme (continuous access to cultural heritage), an initiative to develop and use information technologies to disclose the knowledge inside the vast archives of the Dutch cultural heritage. The HiTiME project is a joint effort of the ILK Research Group of the Tilburg centre for Cognition and Communication at Tilburg University, and IISG, the International Institute of Social History. Since 2011, the HiTiME project also partners with NaCTeM, the National Centre for Text Mining, in Manchester, UK.