Nested Named Entity Recognition in Historical Archive Text

This paper describes work on Named Entity Recognition (NER), in preparation for Relation Extraction (RE), on data from a historical archive organisation. As is often the case in the cultural heritage domain, the source text includes a high percentage of specialist terminology, and is of very variable quality in terms of grammaticality and completeness. The NER and RE tasks were carried out using a specially annotated corpus, and are themselves preliminary steps in a larger project whose aim is to transform discovered relations into a graph structure that can be queried using standard tools. Experimental results from the NER task are described, with emphasis on dealing with nested entities using a multi-word token method. The overall objective is to improve access by non-specialist users to a valuable cultural resource.