Frank,

Just to give you an idea, here you can see an annotated corpus that has been
compiled for Sanskrit:

http://kjc-fs-cluster.kjc.uni-heidelberg.de/dcs/index.php

Rosa

_____

From: Pali@yahoogroups.com [mailto:Pali@yahoogroups.com] On Behalf Of frank
Sent: dilluns, 31 / gener / 2011 15:48
To: Pali@yahoogroups.com
Subject: Re: [Pali] Pali lemmatizer




Hi Rosa,
I don't even know what a lemmatizer is and had to look it up in
http://en.wikipedia.org/wiki/Lemmatisation . But it sure sounds
interesting. How does it work? I'd guess you give it the declension
tables as the rules, and it checks the suffix of every word in the
tipitaka to build a list of potential lemmas? Please let us know what
you find out.
-Frank

On 1/31/2011 12:49 AM, Rosa Grau wrote:
>
> Dear Pali group, just one question to all:
>
> Is there anybody here working on a Pali lemmatizer or does anybody
> know if someone is involved in such a project?
>
> Thank you,
>
> Rosa
>

[Non-text portions of this message have been removed]






[Non-text portions of this message have been removed]