Which ModelDistribution of Dirichlet process clustering should be for text document

["Bae, Jae Hyeon" <me...@gmail.com>]

Hi

I am planning to apply Dirichlet process clustering to multi-document
summarization problem.

Dirichlet process clustering has significantly in-depth mathematical
backgrounds, but I think that I don't have to understand them fully in order
to do my project :)

Have you ever tried Dirichlet process clustering to textual corpus? If so,
which ModelDistribution did you use?

Also, I appreciate so much if you give me advice regarding Dirichlet process
clustering for text data, especially about parameter estimation.

Thank you

Best, Jay