giza-pp

Machine translation toolkit

A toolkit for training statistical machine translation models and word alignment.

GIZA++ is a statistical machine translation toolkit that is used to train IBM Models 1-5 and an HMM word alignment model. This package also contains the source for the mkcls tool which generates the word classes necessary for training some of the alignment models.

GitHub

264 stars
23 watching
83 forks
Language: C++
last commit: over 1 year ago
Linked from 1 awesome list


Backlinks from these awesome lists:

Related projects:

Repository Description Stars
moses-smt/mosesdecoder A software toolkit for machine translation 1,583
moses-smt/nplm A toolkit for training neural network language models 14
musket-ml/segmentation_training_pipeline A tool for defining and running machine learning experiments for image segmentation in Python. 53
moses-smt/salm A tool kit for working with suffix arrays and their applications in empirical language processing. 11
jwieting/para-nmt-50m A collection of pre-trained models and code for training paraphrastic sentence embeddings from large machine translation datasets. 102
sebbekarlsson/glms A language and framework for linear algebra and image manipulation with a focus on simplicity and extensibility. 41
mrpt/mrpt A comprehensive C++ toolkit for mobile robotics and computer vision applications, providing algorithms and data structures for SLAM, motion estimation, image processing, and more. 1,955
ldmt-muri/alignment-with-openfst An implementation of a CRF autoencoder framework for aligning text data 21
sheffieldml/gpmat A Matlab toolbox providing implementations of Gaussian processes and other machine learning tools. 132
redpony/cdec A research platform for machine translation and structured prediction problems. 183
edwardraff/jsat A Java library providing a range of machine learning algorithms and tools for statistical analysis 789
giuse/machine_learning_workbench A comprehensive framework for practical machine learning in Ruby. 20
lmthang/nmt.matlab Provides code to train state-of-the-art Neural Machine Translation systems using Matlab 105
nyu-mll/jiant A toolkit for natural language processing research enabling multitask learning and transfer learning. 1,644
juliastats/mlbase.jl A collection of tools to support the development of machine learning algorithms 185