Easily train your own text-generating neural network of any size and complexity on any text dataset with a few lines of code.

(ARCHIVED) Rant – The all-purpose procedural text library

Chinese version of GPT2 training code, using BERT tokenizer.

Python package to easily retrain OpenAI's GPT-2 text-generating model on new texts

Toolkit for Machine Learning, Natural Language Processing, and Text Generation, in TensorFlow

DELTA is a deep learning based natural language and speech processing platform.

Large-scale pretraining for dialogue

GPT2 for Chinese chitchat/用于中文闲聊的GPT2模型(实现了DialoGPT的MMI思想)

GPT2 for Multiple Languages, including pretrained models. GPT2 多语言支持, 15亿参数中文预训练模型

Code for Defending Against Neural Fake News, https://rowanzellers.com/grover/

Integrating the Best of TF into PyTorch, for Machine Learning, Natural Language Processing, and Text Generation

The codes of paper "Long Text Generation via Adversarial Training with Leaked Information" on AAAI 2018. Text generation using GAN and Hierarchical Reinforcement Learning.

TextGAN is a PyTorch framework for Generative Adversarial Networks (GANs) based text generation models.

Code for PaperRobot: Incremental Draft Generation of Scientific Ideas

A curated list of recent models of text generation and application

word2vec, sentence2vec, machine reading comprehension, dialog system, text classification, pretrained language model (i.e., XLNet, BERT, ELMo, GPT), sequence labeling, information retrieval, information extraction (i.e., entity, relation and event extraction), knowledge graph, text generation, network embedding

A text generation reading list maintained by Tsinghua Natural Language Processing Group.

✍🏻 gpt2-client: Easy-to-use TensorFlow Wrapper for GPT-2 117M, 345M, 774M, and 1.5B Transformer Models 🤖 📝

Code for training and evaluation of the model from "Language Generation with Recurrent Generative Adversarial Networks without Pre-training"

模仿莎士比亚创作戏剧！屌炸天的是还能创作金庸武侠小说！快star，保持更新！！

Text-generation API via GPT-2 for Cloud Run

Accelerated Text helps you to automatically generate natural language descriptions of your data, varying in wording and structure.

Python script to download public Tweets from a given Twitter account into a format suitable for AI text generation.

Set up the CTRL text-generating model on Google Compute Engine with just a few console commands.

Implementations for a family of attention mechanisms, suitable for all kinds of natural language processing tasks and compatible with TensorFlow 2.0 and Keras.

PyTorch implementation of "Lagging Inference Networks and Posterior Collapse in Variational Autoencoders" (ICLR 2019)

DGMs for NLP paper list

Source code and dataset for KDD 2019 paper "Towards Knowledge-Based Personalized Product Description Generation in E-commerce"

OpenAI GPT2 pre-training and sequence prediction implementation in Tensorflow 2.0

pre-training and fine-tuning framework for text generation