-unk flag

Chao Wang wangc at csail.mit.edu
Fri Sep 3 10:27:44 PDT 2004


Could someone please tell me what the -unk flag will do to the probability
model? It seems that, with the -unk flag, the language model will give a very
good probability to unknown words, even when the training sentences don't
contain any unknown words. In fact, I found that the probability for a sentence
in the training data is inferior to that of a sentence composed entirely of
unknown words (the number of words are the same in the two sentences). This is 
quite expected.

Thanks a lot!

Chao
-- 
Chao Wang, PhD
Spoken Language Systems Group
MIT CSAIL
http://www.sls.csail.mit.edu/wangc





More information about the SRILM-User mailing list