[Corpora-List] variant log likelihood calculations

Marco Baroni baroni at sslmit.unibo.it
Wed Dec 15 08:33:00 CET 2004


There in an old posting to this list, by Dunning himself, about various
versions of the log likelihood ratio formula:

http://helmer.hit.uib.no/corpora/1997-2/0148.html

Regards,

Marco






More information about the Corpora-archive mailing list