Semantic indexing via knowledge organization systems: Applying the CIDOC-CRM to archaeological grey literature

The volume of archaeological reports being produced since the introduction of PG161 has significantly increased, as a result of the increased volume of archaeological investigations conducted by academic and commercial archaeology. It is highly desirable to be able to search effectively within and across such reports in order to find information that promotes quality research. A potential dissemination of information via semantic technologies offers the opportunity to improve archaeological practice, not only by enabling access to information but also by changing how information is structured and the way research is conducted. This thesis presents a method for automatic semantic indexing of archaeological grey-literature reports using rule-based Information Extraction techniques in combination with domain-specific ontological and terminological resources. This semantic annotation of contextual abstractions from archaeological grey-literature is driven by Natural Language Processing (NLP) techniques which are used to identify “rich” meaningful pieces of text, thus overcoming barriers in document indexing and retrieval imposed by the use of natural language. The semantic annotation system (OPTIMA) performs the NLP tasks of Named Entity Recognition, Relation Extraction, Negation Detection and Word Sense disambiguation using hand-crafted rules and terminological resources for associating contextual abstractions with classes of the ISO Standard (ISO 21127:2006) CIDOC Conceptual Reference Model (CRM) for cultural heritage and its archaeological extension, CRM-EH, together with concepts from English Heritage thesauri and glossaries. The results demonstrate that the techniques can deliver semantic annotations of archaeological grey literature documents with respect to the domain conceptual models. Such semantic annotations have proven capable of supporting semantic query, document study and cross-searching via web based applications. The research outcomes have provided semantic annotations for the Semantic Technologies for Archaeological Resources (STAR) project, which explored the potential of semantic technologies in the integration of archaeological digital resources. The thesis represents the first discussion on the employment of CIDOC CRM and CRM-EH in semantic annotation of grey-literature documents using rule-based Information Extraction techniques driven by a supplementary exploitation of domain-specific ontological and terminological resources. It is anticipated that the methods can be generalised in the future to the broader field of Digital Humanities