Neural machine Translation
Statistical Machine Translation
Being the initial models for statistical machine translation, word based models are tied to the translation of individual words.
Word Based Models and its 13 sub-topics are the main subject of 396 publications.
Topics in WordBasedModelsIBM Models | Symmetrization | Word Alignment | Dictionaries From Comparable Corpora | Lexical Choice | MT Without Word Alignment
None of the currently competitive machine translation systems are word based models, but nevertheless the principles such as generative modelling and the use of the expectation maximimization algorithm are still core methods today. Moreover, word alignment based on word based models is more often than not the first step in training more complex models.