[SRILM User List] Odd behavior in disambig and OOV words

Andreas Stolcke stolcke at icsi.berkeley.edu
Fri Jan 6 15:12:47 PST 2012


The attached patch seems to fix the problem.

The problem stems from pseudo-random ordering of hypotheses that have
identical scores in viterbi/nbest decoding.
The patch introduces an additional sorting criterion to make the
ordering deterministic.
If you add the option -nbest 10  you see the alternatives that get the
same score, and there are often many.

Andreas



-------------- next part --------------
An embedded and charset-unspecified text was scrubbed...
Name: srilm.patch.txt
URL: <http://www.speech.sri.com/pipermail/srilm-user/attachments/20120106/225fc135/attachment.txt>


More information about the SRILM-User mailing list