[Chicago] python libraries for latent semantic indexing &c.

sheila miguez shekay at pobox.com
Fri Sep 24 17:14:00 CEST 2010

On Thu, Sep 23, 2010 at 9:22 AM, Ed Marshall <esm at logic.net> wrote:
> On Thu, Sep 23, 2010 at 9:13 AM, Daniel Griffin <dgriff1 at gmail.com> wrote:
>> I don't even understand what this is.
> [...]
>>> On Sep 21, 2010 2:53 PM, "sheila miguez" <shekay at pobox.com> wrote:
>>> I would be interested in hearing a talk about how someone has used
>>> python for LSA, LDA, &c. analysis. Playing around myself, I found a
>>> python library called gensim, and a java library called mallet.
>>> http://nlp.fi.muni.cz/projekty/gensim/
> Looks to me (this is definitely not my field either) like semantic analysis
> of arbitrary text; in the gensim case, breaking it down into a vector model
> for representing the information learned:
> http://en.wikipedia.org/wiki/Vector_space_model
> "I Write Like" is what immediately came to mind for me:
> http://iwl.me/
> --
> Ed Marshall <esm at logic.net>
> Felix qui potuit rerum cognoscere causas.
> http://esm.logic.net/

Thanks for following up with the links.

so anyway, it would be fun if someone where to give a talk at an
introductory level on how they are using python to play with concepts
like this.

We do have people where I work using methods like this, though not so
much akin to content similarity in fiction as to ranking
likes/dislikes. I don't often interact with them (not near as much as
in monthly meetings).


More information about the Chicago mailing list