Hello Michael,
At 18:02 +0200 7/12/04, Michael Carl wrote:
The open questions of MT are still open: no-one can properly handle interpersonal/stylistic/pragmatic effects of communication. If one could use EBMT methods to capture style, for example, you'd be doing something that syntax-based transfer approaches would find very hard to do, and SMT approaches would struggle with given their need for large corpora of unitary style.why should EBMT be able to solve problems that even rule-based methods (i.e. 'by hand') cannot solve? You see the misconception:
while SMT is automatizing MT approaches which are outdated in the rule-based paradigm already since 20 or 30 years, EBMT is expected to solve problems
which "no-one can properly handle".
I'm not saying the task of solving the hard problems is that responsibility of EBMT alone. Heavens no! It's the task of everyone.
But there is also an appropriate challenge in Ed's comment: EBMT implements an analogy-like top-down approach (see discussion last year on this list)
and nothing - in principle - prevents to take "interpersonal/stylistic/pragmatic effects of communication" as a guiding principle to find analogies in translated
texts.
Yes. If you want to do work that breaks completely new ground in MT, then focus on style, pragmatics, etc. EBMT in my opinion has the potential to more easily address some of these questions than SMT, because it requires less training data to assemble its pattern knowledge. (But once large training corpora become available in various styles, SMT will go in and do a more comprehensive job.)
But, I guess, first one would have to do this 'by hand' and see exactly how it could work and then wait >20 years to automatise the task ...
You are a pessimist! (Or maybe a realist...)
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
