[Corpora-List] POS-tagging for spoken English and learner English

[Adam Kilgarriff]

                  POS-tagging spoken and learner English
                  ======================================
 
      We have a corpus of spoken English (BASE
http://www.rdg.ac.uk/AcaDepts/ll/base_corpus/ a British equivalent of the
American MICASE http://www.hti.umich.edu/m/micase/ ) and are now assessing
how to (automatically) POS-tag it.   We are also interested in automatic
POS-tagging of learner English (which may involve some of the same
'robustness' issues, even if the linguistics is different)

      Do you have recent experiences of using available taggers on either of
these kinds of data?

	Reports including accuracy figures would be particularly useful.

	Thank you in advance,


		Adam Kilgarriff


====================================================
Adam Kilgarriff
Lexicography MasterClass   http://lexmasterclass.com
Lexical Computing Ltd      http://sketchengine.co.uk
University of Sussex
mailto:adam at lexmasterclass.com    +44 (0)1273 705773
====================================================