A library for efficient similarity search and clustering of dense vectors.

Unsupervised text tokenizer for Neural Network-based text generation.

Vowpal Wabbit is a machine learning system which pushes the frontier of machine learning with techniques such as online, hashing, allreduce, reductions, learning2search, active, and interactive lea…

Non-Metric Space Library (NMSLIB): An efficient similarity search library and a toolkit for evaluation of k-NN methods for generic non-metric spaces.

Unsupervised text tokenizer focused on computational efficiency

Neural Relation Extraction, including CNN, PCNN, CNN+ATT, PCNN+ATT

DAFSA-based dictionary-like read-only objects for Python. Based on `dawgdic` C++ library.

Poincaré Embedding (unofficial)

Load pretrained word embeddings (word2vec, glove format) into torch.FloatTensor for PyTorch

Density Estimation from Approximate Nearest Neighbors