seq2seq-pytorch

Minimalist NMT for educational purposes

Keras, PyTorch, and NumPy Implementations of Deep Learning Architectures for NLP

A PyTorch implementation of the hierarchical encoder-decoder architecture (HRED) introduced in Sordoni et al (2015). It is a hierarchical encoder-decoder architecture for modeling conversation triples in the MovieTriples dataset. This version of the model is built for the MovieTriples dataset.

Neural Machine Translation using LSTMs and Attention mechanism. Two approaches were implemented, models, one without out attention using repeat vector, and the other using encoder decoder architecture and attention mechanism.

Paper Implementation about Attention Mechanism in Neural Network

ICLR_2018_Reproducibility_Challenge : Sketch-RNN

The sequence-to sequence model implemented by pytorch

💬 Sequence to Sequence from Scratch Using Pytorch

Interpretation for english autoencoder (seq2seq model).

Implementation of Selected Published Papers from AI, RL, NLP Conferences and reputed Journals

French to English neural machine translation trained on multi30k dataset.

REST API for training and prediction of seq2seq model