- From: Lieske, Christian <christian.lieske@sap.com>
- Date: Wed, 17 Jul 2013 09:46:17 +0000
- To: Yves Savourel <ysavourel@enlaso.com>, "public-multilingualweb-lt@w3.org" <public-multilingualweb-lt@w3.org>, "serge.gladkoff@gmail.com" <serge.gladkoff@gmail.com>
Hi Yves and Serge, I feel reminded of the discussion on "workflow/multi engine scenarios" that we for example had in the context of http://lists.w3.org/Archives/Public/public-multilingualweb-lt-comments/2013Feb/0018.html Cheers, Christian -----Original Message----- From: Yves Savourel [mailto:ysavourel@enlaso.com] Sent: Mittwoch, 17. Juli 2013 10:00 To: public-multilingualweb-lt@w3.org Subject: RE: MT Confidence definition Hi Serge, > ...it is extremely important where the score comes > from in this case. The value of the annotatorsRef for 'mt-confidence' should tell you that. > ... and then there's another evaluation that comes from a different > system, the steps that are down the stream should be able to distinguish > where the score comes from, and between them scores, too. Currently there is no provision for multiple instances of the MT Confidence annotation on the same content. That would require a standoff markup, like for Provenance and LQI. Cheers, -ys
Received on Wednesday, 17 July 2013 09:46:45 UTC