[SRILM User List] Interpolating LMs with different smoothing

Fed Ang ang.feddy at gmail.com
Tue Jul 17 21:22:58 PDT 2018


I don't know if it has been asked before, but does it make sense to
interpolate on the basis of smoothing instead of domain/genre?  What should
be the assumptions in considering this when the resulting perplexity is
lower than any of the two separately?

Let's say: 5-gram Katz yields 100, and 5-gram Modified KN yields 90
Then best-mix of the two yields 87

On a theoretical perspective, is it sound to simply trust that the
interpolated LM is better/generalizable to different smoothing combinations?

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.speech.sri.com/pipermail/srilm-user/attachments/20180718/774616c2/attachment.html>

More information about the SRILM-User mailing list