Sequence to Sequence Models with PyTorch
Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)
The main features of dsksd/rnn-for-joint-nlu are: Recurrent Neural Networks (RNNs).
Open-source alternatives to dsksd/rnn-for-joint-nlu include: asappresearch/sru — Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755). dasguptar/treelstm.pytorch — Tree LSTM implementation in PyTorch. emited/variationalrecurrentneuralnetwork. maximumentropy/seq2seq-pytorch — Sequence to Sequence Models with PyTorch. salesforce/awd-lstm-lm — LSTM and QRNN Language Model Toolkit for PyTorch. salesforce/pytorch-qrnn — PyTorch implementation of the Quasi-Recurrent Neural Network - up to 16 times faster than NVIDIA's cuDNN LSTM.
