incremental training/align for word alignment

 

The Berkeley Word Aligner

          https://github.com/mhajiloo/berkeleyaligner

          https://github.com/kmccurdy/inc-align

       A small Clojure application which extends the Berkeley Aligner to support incremental alignment, e.g. using an already-trained alignment model to generate alignments on new data without having to retrain the model.

 

GIZA++: Training of statistical translation models.

          http://www.statmt.org/moses/giza/GIZA++.html

          https://github.com/colinal/inc-giza-pp (https://code.google.com/archive/p/inc-giza-pp/)

          Incremental word alignments for SMT using online EM. Currently supports IBM Model 1 and HMM-based word alignments.