Corpora: speech acts and Brill's algorithm

[Matthew T. Bell]

Hi --

I'm investigating applying Brill's algorithm (transformation based
learning) or some other rule learning system to classifying speech acts,
comparing those against a simple n-gram approach.  Does anyone know if
some version of Brill's algorithm has already been applied to this task,
and if so if the system is already available?

Thanks,
Matt

--------------------------------------
Nu sculon herigean	heovonrices Weard
Meotodes mighte		ond His modgethanc

Now we must praise	the Kingdom of Heaven's Sovereign,
The Measurer's power	and his completed design
--First two lines, Caedmon's Hymn
---------------------------------------