Hi, RWTH Aachen University implemented extraction of discontinuous phrases and decoding with source-side gaps in the Jane toolkit [www.hltpr.rwth-aachen.de/jane/]. We did not see any clear improvements over standard phrase-based setups in our experiments, though.
Some results were published in PBML: M. Huck, E. Scharwächter, and H. Ney. Source-Side Discontinuous Phrases for Machine Translation: A Comparative Study on Phrase Extraction and Search. The Prague Bulletin of Mathematical Linguistics, number 99, pages 17-38, Prague, Czech Republic, April 2013. http://www.hltpr.rwth-aachen.de/publications/download/848/Huck-PBML-2013.pdf The Jane Hiero implementation yields better translation quality on Chinese-English. But note that RWTH did not modify Jane's phrase-based decoder to support target-side gaps. I would be very much interested in seeing whether other groups than Stanford achieve encouraging results with discontinuous phrases in their toolkits. Erik Scharwächter wrote most of the code related to discontinuous phrases in the Jane toolkit as part of his Bachelor's thesis. I don't know how you define a "massive undertaking", but an excellent undergraduate student can obviously implement it, run some experiments and write a thesis about it within a limited amount of time. Cheers, Matthias On Sun, 2013-11-03 at 20:34 -0800, Kenneth Heafield wrote: > Hi, > > I'll throw in the anecdote that gappy phrases are currently not in use > at Stanford. My predecessor told me that it took a lot longer and only > improved BLEU slightly on Chinese-English. But it's also possible that > something didn't get passed down correctly from Michel to my predecessor > to me. . . > > Kenneth > > On 11/03/13 14:18, Read, James C wrote: > > My understanding is that they used a similar approach as the grammar > > extraction to extract the gappy phrases. Would it be a massive undertaking > > to get Moses to support this? > > > > James > > ________________________________________ > > From: Barry Haddow [bhad...@staffmail.ed.ac.uk] > > Sent: 30 October 2013 09:26 > > To: Read, James C > > Cc: moses-support@mit.edu > > Subject: Re: [Moses-support] gappy phrases > > > > No, but it does support hiero and syntax models. > > > > On 29/10/13 22:23, Read, James C wrote: > >> Hi, > >> > >> does anybody know if Moses supports gappy phrases > >> http://www-nlp.stanford.edu/pubs/naacl10-discontinuous_phrases.pdf > >> > >> James > >> -- The University of Edinburgh is a charitable body, registered in Scotland, with registration number SC005336. _______________________________________________ Moses-support mailing list Moses-support@mit.edu http://mailman.mit.edu/mailman/listinfo/moses-support
