PAR Transformer XL An implementation of the Pay-Attention-as-Required Transformer. Shakespeare Translator An attention based translator to rewrite modern day english into Shakespearian english. Adaptive Softmax A TF2.0+ implementation of the Adaptive Softmax layer. Locality Sensitive Hashing A tutorial on Locality Sensitive Hashing, with applications to document similarity and vector comparison. SentencePiece from Scratch A dissection of SentencePiece, and a pythonb-based reconstruction. Word2Vec An implementation of the popular paper "Distributed Representations of Words and Phrases and their Compositionality."
