[Corpora-List] Looking for a high accuracy Chinese segmenter

"Венцислав Жечев (Ventsislav Zhechev)" contact at VentsislavZhechev.eu
Wed Jan 22 08:21:29 UTC 2014


Hi Remus,

We have been successfully using KyTea (http://www.phontron.com/kytea/) for a few years now in production at Autodesk. It was originally designed for handling JA, but they provide ready models for ZH, too. We use the segmenter during MT training and we are happy with the results.


Cheers,

Ventzi

–––––––
Dr. Ventsislav Zhechev
Computational Linguist
Language Technologies, Localisation Services

MAIN +41 32 723 91 22
FAX +41 32 723 93 99

http://VentsislavZhechev.eu

Autodesk, Inc.
Rue de Puits-Godet 6, CP 35
2002 Neuchâtel, Switzerland
www.autodesk.com



-------------- next part --------------
A non-text attachment was scrubbed...
Name: pastedGraphic.pdf
Type: application/pdf
Size: 18371 bytes
Desc: not available
URL: <http://listserv.linguistlist.org/pipermail/corpora/attachments/20140122/ecd49864/attachment.pdf>
-------------- next part --------------


21.01.2014, ? 12:00, corpora-request at uib.no ???????(?):

> ----------------------------------------------------------------------
> 
> Message: 1
> Date: Mon, 20 Jan 2014 16:17:01 +0100
> From: Remus Mois <rmois at ivona.com>
> Subject: [Corpora-List]  Looking for a high accuracy Chinese segmenter
> To: "corpora at uib.no" <corpora at uib.no>
> 
> I know there are many out there, I would like to identify the best known ones, any help would be much appreciated.
> 
> --
> Best regards,
> Remus 
> 
> Remus Mois
> Software Development Manager
> Ivona Software, an Amazon Company

-------------- next part --------------
_______________________________________________
UNSUBSCRIBE from this page: http://mailman.uib.no/options/corpora
Corpora mailing list
Corpora at uib.no
http://mailman.uib.no/listinfo/corpora


More information about the Corpora mailing list