A translation method that learns likely word matches from bilingual text.
SMT is like a tired subtitler with a giant stack of old DVDs. It sees “I’m fine” and bets on the line it has seen most.
It powered early web and document translation. It needed lots of matched bilingual text, then NMT mostly took over.
MT
SMT was the main MT route before neural networks.
NMT
NMT used one neural network instead of the old SMT setup.
N-gram LM
N-gram LM often gave each possible translation a smoothness score.
IBM Models
IBM Models laid the base for word alignment and translation odds.