Corpora: Negative mutual information?

David Campbell campbed at flux.cpmc.columbia.edu
Thu Mar 8 09:41:40 UTC 2001


I have a question about calculating mutual information for bigrams in
text.  According to every definition I've seen of MI, the values are
non-negative.  However, I've found that for some bigrams made of common
words in very uncommon bigrams, the value is less than zero.  Does anyone
know how to interpret a negative mutual information?

Thanks
David Campbell


The Twelve Months

Snowy, Flowy, Blowy,
Showery, Flowery, Bowery,
Hoppy, Croppy, Droppy,
Breezy, Sneezy, Freezy.
GEORGE ELLIS



More information about the Corpora mailing list