The Automatic Grammatical Tagging of the LOB Corpus

In collaboration with the English Department, University of Oslo, and the Nowegian Computing Centre for the Humanities, Bergen we have been engaged in the automatic grammatical tagging of the LOB (LancasterOslo/Bergen) Corpus of British English. The computer programs for this task are running at a success rate of approximately 96.7% and a substantial part of the 1,000,000-word corpus has already been tagged. The purpose of this paper is to give an account of the project, with special reference to the methods of tagging we have adopted.