RE: tlug: text analysis

[David Dibben <dibben@example.com>]

On 18-Nov-98 Ulrike Schmidt wrote:
> Does anyone know of a program that chops texts into sentences, and,
> (more important since the first thing should not be so difficult): chops
> sentences into their basic sentences? Maybe even recording the structure
> of the original sentence?
> 
> And of a program that transforms verbs, nouns, adverbs into their
> standard dictionary forms?


You may want to have a look at the info on the British National Corpus page.
They have some info on a program, CLAWS, which parses text and produces a
tagged SGML file. I could find any info on where to get this program, or even
if it is available -- but I didn't spend too long searching.

http://info.ox.ac.uk/bnc/what/garside_allc.html  

also there was some stuff about grammatical tagging

http://info.ox.ac.uk/bnc/whay/gramtag.html

Not supprisingly the British National Corpus only deals with English.


David

----------------------------------
E-Mail: David Dibben <dibben@example.com>
Date: 18-Nov-98
Time: 13:46:07
----------------------------------
----------------------------------------------------------------
Next Nomikai: 20 November, 19:30   Tengu TokyoEkiMae 03-3275-3691
Next Technical Meeting: 12 December, 12:30 HSBC Securities Office
----------------------------------------------------------------
more info: http://tlug.linux.or.jp Sponsors: PHT, HSBC Securities