* Compatibility with OpenFst version 1.7.6 (1.3.9) * Compatibility with OpenFst version 1.7.4 (1.3.8) * Modernizations to test scripts (1.3.7) * Compatibility with OpenFst version 1.7.3 (1.3.7) * Compatibility with OpenFst version 1.7.1 (1.3.6) * New method for ngram-shrink to allow pruning of n-grams in a list (1.3.5) * New method for ngram-merge to allow replacement of lower orders of an n-gram model with the lower orders of another model (1.3.5) * Compatibility with OpenFst version 1.7.0 (1.3.5) * Avoid copying in the context library (1.3.4) * Substantial rewrite of the ngram-marginalize methods; the algorithm now has improved efficiency and stability, and no longer needs the --iteration flag (1.3.3) * Minor floating point stability and error handling updates (1.3.3) * Update to ngram-shrink methods to allow specification of a minimum order to prune (1.3.3) * Some changes to container types, following usage recommendations. (1.3.3) * Compatibility with OpenFst version 1.6.0 (1.3.2) * Improved reading of large files of ngram counts with ngramread (1.3.1) * Fixed ill-formatting in error handling (1.3.1) collisions with multiple processes (1.3.1) * Templated Arc to provide new hist-arc counting, supporting fractional count based Katz backoff models (1.3.0) * Updated error handling (1.3.0) * Updated code to better conform to Google C++ guidelines (1.3.0) * Added Bayesian model merging (1.3.0) * Some re-factoring of functions to improve efficiency, particularly those for distributed training, such as ngram-complete and ngram-split (1.3.0) * Updated unit tests to run more quickly and to be less Bash-specific (1.3.0) * Port to C++11 (1.2.0) * Port to C++11 addenda (1.2.1) * Compatibility with OpenFst version 1.5.1 (1.2.2) * Substantially refactored code to allow for easy distributed model building (1.1) * Included a 'convenience' shell script bin/ngram.sh that runs some common pipelines of commands, e.g., from text file to pruned language model (1.1) Shell script provides illustration of distributed model building utilities. * Functions to re-estimate smoothed n-gram models to impose marginal distribution constraints (1.1) * Initial public release (1.0)