Hi, this paper:
Word-Based Alignment, Phrase-Based Translation: What's the Link?<http://www.mt-archive.info/AMTA-2006-Lopez.pdf>With Philip Resnik. In *Proceedings of AMTA* <http://amta2006.amtaweb.org/index.htm>, pages 90–99, August 2006 has a nice discussion about which features can be turned off at what loss (at the end of the paper, the main focus is word alignment quality). -phi On Fri, Mar 23, 2012 at 3:08 AM, Panos Kanavos <[email protected]>wrote: > Hi all, > > According to Moses manual, the 5 scores of each translation table are the > following: > > 1. inverse phrase translation probability > 2. inverse lexical weighting > 3. direct phrase translation probability > 4. direct lexical weighting > 5. phrase penalty > > If I wanted to experiment manually with these weights, which ones would > affect > mostly the behavior of the system and the translation results? Also, are > there > any general suggested or sensible thresholds independent of the language? > > Thanks. > > Panos > > _______________________________________________ > Moses-support mailing list > [email protected] > http://mailman.mit.edu/mailman/listinfo/moses-support >
_______________________________________________ Moses-support mailing list [email protected] http://mailman.mit.edu/mailman/listinfo/moses-support
