Hi Olga!

You can find a whole lot of stemming algorithms at
http://snowball.tartarus.org/texts/stemmersoverview.html.  If you can
tokenize your text into words, the stemmer will attempt to derive the base
form.

Good luck,
Nic.

> Hi all,
>
> I am working on my own "pet" project, and an issue came up: is there
> such a thing as an available to public language normalization module,
> which would process in-coming text and bring it to a set of dictionary
> forms (e.i. verb infinitives etc.). Ideally needed for as many languages
> as possible. If not
>
> Thanks,
>
> Olga Beregovaya
>
> World Wide Localization
>
> Autodesk, Inc.
>
>

-- 
nicholas cottrell <[EMAIL PROTECTED]>
transmachina.com
stockholm, sweden
phone +46 702 630 451

_______________________________________________
MT-List mailing list
[EMAIL PROTECTED]
http://www.computing.dcu.ie/mailman/listinfo/mt-list

Reply via email to