Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)

See https://meta.wikimedia.org/wiki/Research:Modeling_Talk_Page_Abuse

Models and examples built with TensorFlow

Collection of generative models, e.g. GAN, VAE in Pytorch and Tensorflow.

Semantic natural language understanding at scale using Spark, machine-learned annotators and deep-learned ontologies

Auto-WEKA

Finite state dictionaries in Java

Daemon for easy but powerful stats aggregation

Cascading is a feature rich API for defining and executing complex and fault tolerant data processing flows locally or on a cluster.