NLP & Seq2Seq codes

Name	Description	Illustration
Pytorch-nmt	Vanilla MLE and RAML implementation
QRNN.pytorch	PyTorch implementation of the Quasi-Recurrent Neural Network - up to 16 times faster than NVIDIA's cuDNN LSTM
Dynamic-Evaluation.pytorch	Dynamic evaluation for pytorch language models, now includes hyperparameter tuning
Breaking the softmax Bottleneck.pytorch	Implementation of Breaking the Softmax Bottleneck: A High-Rank Language Model
Review Networks.Torch	Review Network for Caption Generation
Words or Characters gating.theano	Fine-grained Gating for Reading Comprehension
FastText	Library for fast text representation and classification.
Sent2Vec	General purpose unsupervised sentence representations
NMT.Pytroch	pytorch attentional NMT(with NLL, MRT, REINFORCE, MIXER training objectives)
Subword-NMT preprocessing	This repository contains preprocessing scripts to segment text into subword units. The primary purpose is to facilitate the reproduction of our experiments on Neural Machine Translation with subword units
BSO	Code for Sequence-to-Sequence Learning as Beam-Search Optimization (Wiseman and Rush, 2016).
MIXER.torch	Mixed Incremental Cross-Entropy REINFORCE ICLR 2016
MUSE.pytorch	A library for Multilingual Unsupervised or Supervised word Embeddings
Structured-Self-Attentive-Sentence-Embedding.pytorch	An open-source implementation of the paper A Structured Self-Attentive Sentence Embedding published by IBM and MILA. Requires spaCy as well.
nmt.pytorch	Neural Machine Translation Framework in PyTorch
NeuralDialog-CVAE.pytorch	Knowledge-Guided CVAE for dialog generation
bandit-nmt.pytorch	This is code repo for our EMNLP 2017 paper "Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback", which implements the A2C algorithm on top of a neural encoder-decoder model and benchmarks the combination under simulated noisy rewards.
Diverse Beam Search.torch	This code implements Diverse Beam Search (DBS) - a replacement for beam search that generates diverse sequences from sequence models like LSTMs. This repository lets you generate diverse image-captions for models trained using the popular neuraltalk2 repository. A demo of our implementation on captioning is available at dbs.cloudcv.org
SentEval.pytorch	SentEval is a library for evaluating the quality of sentence embeddings. We assess their generalization power by using them as features on a broad and diverse set of "transfer" tasks (more details here). Our goal is to ease the study and the development of general-purpose fixed-size sentence representations.
SRU.pytorch	Training RNNs as Fast as CNNs (https://arxiv.org/abs/1709.02755)
Listen-Attend-and-Spell-Pytorch	Listen Attend and Spell (LAS) implement in pytorch
rnn.wgan.Tensorflow	Code for training and evaluation of the model from "Language Generation with Recurrent Generative Adversarial Networks without Pre-training" https://arxiv.org/abs/1706.01399
InferSent.pytorch	Sentence embeddings (InferSent) and training code for NLI.
fairseq.Torch	Facebook AI Research Sequence-to-Sequence Toolkit
wordemb.PyTorch	Load pretrained word embeddings (word2vec, glove format) into torch.FloatTensor for PyTorch
seq2seq-attn.Torch	Sequence-to-sequence model with LSTM encoder/decoders and attention
gated-attention-reader.PyTorch	Tensorflow/Pytorch implementation of Gated Attention Reader
glove.python	Toy Python implementation of http://www-nlp.stanford.edu/projects/glove/
Variational-LSTM-Autoencoder.Torch	Variational Seq2Seq model
Hard-Aware-Deeply-Cascaed-Embedding.c++	source code for the paper "Hard-Aware-Deeply-Cascaed-Embedding"
seq2seq-intent-parsing.PyTorch	Intent parsing and slot filling in PyTorch with seq2seq + attention
diverse-beam-search.Torch
sentiment-neuron.PyTorch	Pytorch version of generating-reviews-discovering-sentiment : https://github.com/openai/generating-reviews-discovering-sentiment
actor-critic-public.theano	The source code for "An Actor Critic Algorithm for Structured Prediction"
TorchGlove.PyTorch	PyTorch implementation of Global Vectors for Word Representation. http://suriyadeepan.github.io/2016-06-28-easy-seq2seq/
TreeLSTM.PyTorch	An attempt to implement the Constinuency Tree LSTM in "Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks"
treelstm.pytorch	A PyTorch based implementation of Tree-LSTM from Kai Sheng Tai's paper Improved Semantic Representations From Tree-Structured Long Short-Term Memory Networks.
OpenNMT.PyTorch	This is a Pytorch port of OpenNMT, an open-source (MIT) neural machine translation system. Full documentation is available here.
seq2seq.pytorch	This is a complete suite for training sequence-to-sequence models in PyTorch. It consists of several models and code to both train and infer using them.
attention-is-all-you-need.pytorch	This is a PyTorch implementation of the Transformer model in "Attention is All You Need" (Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Lukasz Kaiser, Illia Polosukhin, arxiv, 2017).
nmt-seq2seq.PyTorch	seq2seq model written in Pytorch
seq2seq.Tensorflow	Attention-based sequence to sequence learning
DenseContinuousSentances.Tensorflow	Working towards implementing Generating Sentences from a Continuous Space but with DenseNet
bi-att-flow.Tensorflow	Bidirectional Attention Flow