Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

Python package built to ease deep learning on graph, on top of existing DL frameworks.

Models, data loaders and abstractions for language processing, powered by PyTorch

Python library to compute knowledge graph embeddings

Meandering In Networks of Entities to Reach Verisimilar Answers

Tools for state of the art Knowledge Base Completion.

Hierarchical Models for Sentiment Analysis in Pytorch

Pytorch implementation of Hierarchical Encoder Decoder Sequence to Sequence Model

Misc script in one place

Source code for all models from our IJCAI 2018 Paper "Mitigating the Effect of Out-of-Vocabulary Entity Pairs in Matrix Factorization for Knowledge Base Inference"