Synopsis
Named entity tagging of historical parliamentary proceedings
Description
BOPCRIS (British Official Publications Collaborative Reader Information Service) aims to provide online access to British official publications from 1688-1995. The LTG's role in this project is to develop a named entity tagger which can recognise people and place names in parliamentary proceedings spanning this period. The NER problem is complicated by the variation in spelling and language use in the historical text, and by the noise introduced by the OCR.
Start Date:
01 August 2006
End Date:
31 December 2006
|