DFKI-LT - Approximating Context-Free by Rational Transduction for Example-Based MT
Approximating Context-Free by Rational Transduction for Example-Based MT
1 Proceedings of the 39th Annual Meeting and 10th Conference of the European Chapter, Workshop proceedings: Data-Driven Machine Translation, July 5-11,
Existing studies show that a weighted context-free transduction of reasonable quality can be effectively learned from examples. This paper investigates the approximation of such transduction by means of weighted rational transduction. The advantage is increased processing speed, which benefits real-time applications involving spoken language.
Files: BibTeX, Nederhof:2001:ACFa.pdf