Output details

A pilot investigation of information extraction in the semantic annotation of archaeological reports

<15> An outcome of PhD research associated with the AHRC funded STAR project in collaboration with English Heritage and Archaeology Data Service. Distinct from Output3, this paper focuses on natural language processing of archaeology grey literature, in order to enable cross-search with datasets via the conceptual framework. It is the first paper to discuss particular issues for information extraction posed by archaeology domain. Earlier version was published in Proc. Metadata and Semantics Research (MTSR 2011, 30% acceptance for full papers). This research has contributed to a big data AHRC proposal (September 2013) with University of the Arts and Glasgow University.