2

If I generate a language model with SRILM's ngram-count and then use ngram -unk -ppl text -lm model to get log probabilities and perplexity values, are the perplexities normalized for sentence length?

3

Hope it is not too late.

Both ppl and ppl1 are normalized according http://www.speech.sri.com/projects/srilm/manpages/srilm-faq.7.html , which is called entropy rate.

1
  • @L3viathan Please post the answer when you find it... Sep 21 '15 at 3:16

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.