Excavating Grey Literature: A case study on rich indexing of archaeological documents by the use of Natural Language Processing Techniques and Knowledge Based resources.

This paper describes the use of Information Extraction (IE), a Natural Language Processing (NLP)
technique to assist ‘rich’ semantic indexing of diverse archaeological text resources. Such unpublished online
documents are often referred to as ‘Grey Literature’. Established document indexing techniques are not sufficient to
satisfy user information needs that expand beyond the limits of a simple term matching search. The focus of the research is to
direct a semantic-aware 'rich' indexing of diverse natural language resources with properties capable of satisfying
information retrieval from on-line publications and datasets associated with the Semantic Technologies for Archaeological
Resources (STAR) project in the UoG Hypermedia Research Unit.