[Topic-models] queries regarding working principle of lda

rohit nagori rohit007.nagori at gmail.com
Fri Aug 27 09:21:01 EDT 2010


I am deeply interested in understanding the working principle of LDA.
After reading the paper written by David M. Blei,Andrew Y. Ng,Michael I.
Jordan,*Latent Dirichlet Allocation,*Journal of Machine Learning Research 3
(2003) 993-1022,
i got the following queries:
1.what is the significance of variational dirichlet parameter, Gamma. how it
is helpful in calculating the inference from the test set. i am unable to
understand the significance of   name.gamma and name .likelihood files that
we are getting in inference.
2. how we can prioritize the words in a topic based on their appearance in
title, subtitle, or abstract of a document.
3.how we can find the documents containing the words in a topic

looking forward for your reply.

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.cs.princeton.edu/pipermail/topic-models/attachments/20100827/2c66b21b/attachment.htm>

More information about the Topic-models mailing list