> Given the above trend, I think an effective response is to explicitly[...]say in an EBMT paper "yes I am doing EBMT but creating the example phrases and their translation by hand; some SMT is creating thethe bigger point, though, is: why should one not make comparisons to
SMT-style EBMT? A serious weakness of EBMT has always been the
bottleneck of building the example patterns and their translations
manually.
Unless I've badly misunderstood all the papers I have read, EBMT does not build anything by hand. Existing translated texts are used as sources of examples which are sought out and reused on the fly. In some reported experiments, the examples were handpicked, or pruned to get rid of awkward cases, but I don't think this idea is taken seriously as the way to do EBMT.
I stand corrected. Thanks Harry. In that case, it would be nice to know how the learning methods of SMT and EBMT differ, and which type gives better (more comprehensive/useful/etc.) results for how much (effort/computation/data/etc.).
One recent flavour of EBMT has been to extract similar examples beforehand and generalise them, giving translation templates which could be likened to old- fashioned transfer rules. But again this is done automatically. This seems to me to be very close to the latest trend in phrase-based SMT, and if I had been someone who had worked on this idea and calling it EBMT I would find it quite galling not to be cited, or being asked to compare it with an approach that actually postdates what I had done.
Could one say that the two are growing together? That example-pattern-based SMT will increasingly merge with EBMT (or vice versa)? As predicted...
E
-- Eduard Hovy email: [EMAIL PROTECTED] USC Information Sciences Institute tel: 310-448-8731 4676 Admiralty Way fax: 310-823-6714 Marina del Rey, CA 90292-6695 http://www.isi.edu/natural-language/nlp-at-isi.html
_______________________________________________ MT-List mailing list [EMAIL PROTECTED] http://www.computing.dcu.ie/mailman/listinfo/mt-list
