SLM is a Bayesian skipgram language model based on hierarchical Pitman-Yor processes. It facilitates multiple backoff strategies, interpolation strategies, and offers tools to train and evaluate language models, and rescore nbest lists

Skipgram with Hierarchical Softmax

Efficient learning of word representations

Colibri core is an NLP tool as well as a C++ and Python library for working with basic linguistic constructions such as n-grams and skipgrams (i.e patterns with one or more gaps, either of fixed or dynamic size) in a quick and memory-efficient way. At the core is the tool ``colibri-patternmodeller`` whi ch allows you to build, view, manipulate a…

A word2vec negative sampling implementation with correct CBOW update.