Re: Corpora: European language lemmatisers

Jean Veronis (Jean.Veronis@newsup.univ-mrs.fr)
Wed, 10 Nov 1999 18:23:43 +0100

At 16:52 10/11/99 +0000, Steffan Corley wrote:
>If anyone can suggest a more appropriate list to send this too...

For French, you can use the LN list <ln@cnusc.fr>.

Info at: http://www.biomath.jussieu.fr/~pz/LN-F/

>We are looking for fast lemmatisers or stemmers for various European
>languages, including French, Italian, Spanish, German, Dutch and
>Swedish. Ideally, we would like to license a single product which can cope
>with most or all of these languages.

The best technology for French, in my view, is that of the Synapse company
(http://www.synapse-fr.com/), who developped the Word2000 spelling and
grammatical tools. I personnally use their tagger/lemmatiser ("Cordial
universités"), which is absolutely astounding in terms of accuracy -- I get
no royalties :-)

although I am not sure about which. You can contact Dominique LAURENT
<dlaurent@synapse-fr.com> for details.

Best,
Jean Véronis

Jean Véronis, Professeur de Linguistique et Informatique

Directeur du Centre Informatique pour les Lettres et Sciences Humaines
Université de Provence
29 av. Robert Schuman
13621 Aix-en-Provence Cedex 1, France

tel: +33 (0) 4 42 95 31 35
fax: +33 (0) 4 42 95 34 95
email: veronis@up.univ-mrs.fr

http://www.up.univ-mrs.fr/~veronis/