Deepening wisdom or compromised principles?-the hybridization of statistical and symbolic MT systems
Eduard H. Hovy · IEEE Expert · 1996
Departing from your principles is hard. The frequency and volume with which the principles of statistical and symbolic MT were repeated during the Statistics Wars means impressive-sounding arguments will continue for a while. But it is perhaps more instructive to consider what happens in practice. Baldly stated, if you want to build a non-toy MT system-a system with more than approximately 5,000 lexical items-that handles previously unseen input robustly, you always end up including some statistics-based modules or knowledge. And if you want a reasonable level of output quality, you always end up including some symbolic/linguistically motivated knowledge or modularization.