> Ariadna Font Llitjos wrote: > >I'm actually working on how to use user feedback to directly and > >automatically improve a translation grammar. > > > >I have a paper accepted in LREC04 that describes the tool I built to allow > >users to correct translations (the TCTool). It's already linked from > >my web-site: http://www-2.cs.cmu.edu/~aria/publications.html > > > >And I'm currently writing a paper that focuses more on the back-end > >details, which I could send you as soon as it gets accepted to a > >conference,
Christian Boitet <[EMAIL PROTECTED]> wrote: > That is another way to attack the problem of improving MT quality > output, but it is not of the sort envisaged by the original > question. However, it supposes (in general) that the user is a > professional translator knowing very well both languages, while the > ID approach is more for non-professionals knowing the source language > only. That is a good statement. See my book chapter that describes the levels of user interactive MT postediting based on Inbound translation (ie, assimilation, content gisting) vs Outbound translation (ie, dissemination, translation for publication) approaches. ALLEN, Jeffrey. 2003. Post-editing. In Computers and Translation: A Translators Guide. Edited by Harold Somers. Benjamins Translation Library, 35. Amsterdam: John Benjamins. (ISBN 90 272 1640 1). http://www.benjamins.com/cgi-bin/t_bookview.cgi?bookid=BTL_35 Then map the different types of user interaction (input source text to output target text) onto these different approaches. This should give a reasonable matrix of user interaction to work with. Also take a look at the following presentation where I described the impact of the horizontal (relationship) axis (human-human, machine-machine, human-machine) upon the vertical (technology) axis and the effect on technology implementation projects. ALLEN, Jeffrey. 1999. Implementing Controlled Language and Machine Translation in the automotive industry. Invited talk at the 1st Multilingual Documentation for the Automotive Industry TOPTEC Symposium. Co-sponsored by the Society of Automotive Engineers (SAE), the Localisation Industry Standards Association (LISA), and ALPNET. Held 21-22 October 1999 in Amsterdam, The Netherlands. Jaap van der Meer also hints towards this in one of his recent articles / presentations. I can't remember which one specifically. Jaap van der Meer: The Electric Word and the Semantic Web. "Perspectives on Machine Translation" : a special Machine Translation supplement to issue #62 of Multilingual Computing & Technology. http://www.multilingual.com/machineTranslation62.htm Jaap Van der Meer. Changing Industry Needs, new Technology Suppliers. Presented at panel session of LangTech2003. Paris, 25 Nov 2003. Jaap van der Meer. At Last Translation Automation Becomes a Reality: an Anthology of the Translation Market. In proceedings of EAMT/CLAW 2003. Jaap van der Meer. The Business Case for MT: The Breakthrough Is for Real. LISA Newsletter XII-2_6. Regards, Jeff Jeff Allen [EMAIL PROTECTED] My publications page: http://www.geocities.com/jeffallenpubs/ _______________________________________________ MT-List mailing list [EMAIL PROTECTED] http://www.computing.dcu.ie/mailman/listinfo/mt-list
