Github user jkbradley commented on the pull request:
https://github.com/apache/spark/pull/7801#issuecomment-126481809
This looks good, but it made me realize that gensim defines log perplexity
as the negation of the log perplexity in the Online LDA paper's Eq 15. I
prefer the Online LDA paper way, since low perplexity sounds like a good thing
to me (whereas with gensim, high perplexity is better). I checked Stanford
NLP, and they also say lower perplexity is better. Can you please modify the
logPerplexity code to negate the returned value?
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
