A masked language modeling objective to train a model to predict any subset of the target words, conditioned on both the input text and a partially masked target translation.

A script that creates train, valid and test datasets for the ranking task from Ubuntu corpus dialogs.

Code and Data for ACL 2019 "Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention"

Dirichlet Latent Variable Hierarchical Recurrent Encoder-Decoder in dialogue generation（EMNLP2019）

github for paper "Automatically Learning Data Augmentation Policies for Dialogue Tasks [Tong Niu and Mohit Bansal] (EMNLP 2019)" (code and augmented data coming soon)

Python package built to ease deep learning on graph, on top of existing DL frameworks.

sketch + style = paints 🎨 (TOG2018/SIGGRAPH2018ASIA)

tensorboard for pytorch (and chainer, mxnet, numpy, ...)

Paper List for Style Transfer in Text

中文自然语言处理工具包 Toolkit for Chinese natural language processing