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.
本文介绍了两种用于统计机器翻译的增量对齐工具:BerkeleyWordAligner的扩展版本及GIZA++。前者可在已训练模型的基础上进行增量对齐,无需重新训练;后者支持IBM Model1和基于隐马尔可夫模型的对齐。
422

被折叠的 条评论
为什么被折叠?



