- From: Dr. David Filip <David.Filip@ul.ie>
- Date: Tue, 5 Jun 2012 09:35:10 +0100
- To: Yves Savourel <ysavourel@enlaso.com>
- Cc: public-multilingualweb-lt@w3.org
- Message-ID: <CANw5LKmTGLJ9p9a4qSbTsbpqx2n8tafS7p62CMq3npxMddiFbA@mail.gmail.com>
Thanks Yves, that is a nice consumer.. @Yves, @Milan, you guys work on the M4Loc project, would there be an interest? Perhaps Achim himself to consume such an XLIFF on Moses training, or even runtime for real time disambiguation via a property bag (as I mentioned in a call Asia online seem to be doing this kind of thing) Rgds dF Dr. David Filip ======================= LRC | CNGL | LT-Web | CSIS University of Limerick, Ireland telephone: +353-6120-2781 *cellphone: +353-86-0222-158* facsimile: +353-6120-2734 mailto: david.filip@ul.ie On Tue, Jun 5, 2012 at 4:53 AM, Yves Savourel <ysavourel@enlaso.com> wrote: > Hi Felix, Pedro, Tadej, all, > > >> 4) Would 1-2 be consumed by an MT tool, or by other tools? > >> > > These can be basically consumed by language processing tools, > > like MT, and other Linguistic Technology that needs content or > > semantic info. For instance Text Analytics, Semantic search, etc.. > > In the localization chains, these information can be also used > > by automatic or semiautomatic processes (like selection of > > dictionaries for translations, or selection of translators/revisers > > by subject area) > > FWIW: I've listed an Okapi 'step' as consumer for namedEntity and > textAnalysisAnnotation: It would send data to process in HTML format to the > producer (e.g. Enrycher), get back the annotated HTML, read the annotation > and store them in its internal format, and then a next step could use the > annotations to produce some type of output along with a translation kit: > notes in an XLIFF document, look-up file, etc. something that could be used > by translators for reference. > > Cheers, > -ys > > >
Received on Tuesday, 5 June 2012 08:36:19 UTC