This work is supported by the
IRCSET Embark Initiative
(basic research grant SC/02/298 and postdoctoral fellowship P/04/232).
The training and test data used in this reseach is based on
the British National Corpus (BNC)
,
distributed by Oxford University Computing Services on behalf of the
BNC Consortium.
We thank Djamé Seddah for helping us to run the XLE parsing on the
SFI/HEA
Irish Centre for High-End Computing (ICHEC)
and
the authors wish to acknowledge ICHEC
for the provision of computational facilities and support.