lzy's repositories
ACLPUB
The official tool for creating proceedings for conferences of the Association for Computational Linguistics (ACL).
GPT2-Chinese
Chinese version of GPT2 training code, using BERT tokenizer.
converse_reading_cmr
code, data, and model for ACL-19 paper "Conversing by Reading: Contentful Neural Conversation with On-demand Machine Reading"
Jax
利用PMI(Pointwise Mutual Information)、左右信息熵发现新词
pytorch-beginner
pytorch tutorial for beginners
mosesdecoder
Moses, the machine translation system
practical-pytorch
PyTorch tutorials demonstrating modern techniques with readable code
PyTorchZeroToAll
Simple PyTorch Tutorials Zero to ALL!
tensor2tensor
Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research.
torchbearer
torchbearer: A model training library for PyTorch
nips_convai2_resource
Maintain resources for NIPS 2018 Competition ConvAi2, including dataset url, papers, etc
Hierarchical-Seq2Seq
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.
diverse-beam-search
:mag: :shipit: Decoding Diverse Solutions from Neural Sequence Models
keras-rl
Deep Reinforcement Learning for Keras.
SelfAttentive
Implementation of A Structured Self-attentive Sentence Embedding
GANotebooks
wgan, wgan2(improved, gp), infogan, and dcgan implementation in lasagne, keras, pytorch
ubuntu-ranking-dataset-creator
A script that creates train, valid and test datasets for the ranking task from Ubuntu corpus dialogs.
Variational-AutoEncoder-for-Dialogue-Generation
Variational Auto-Encoder for Dialogue Generation Models & Experiments
TensorFlow-Examples
TensorFlow Tutorial and Examples for beginners
CarND-Behavioral-Cloning-P3
Starting files for the Udacity CarND Behavioral Cloning Project
GAN-discussions
GAN讨论群讨论汇总的地方
visdom
A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy.