There are 53 repositories under natural-language-generation topic.
Go to https://github.com/pytorch/tutorials - this repo is deprecated and no longer maintained
YAYI 2 是中科闻歌研发的新一代开源大语言模型,采用了超过 2 万亿 Tokens 的高质量、多语言语料进行预训练。(Repo for YaYi 2 Chinese LLMs)
Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.
Neural question generation using transformers
This Word Does Not Exist
📖 Paper reading list in dialogue systems and natural language generation (constantly updating 🤗).
💁 Awesome Treasure of Transformers Models for Natural Language processing contains papers, videos, blogs, official repo along with colab Notebooks. 🛫☑️
Accelerated Text is a no-code natural language generation platform. It will help you construct document plans which define how your data is converted to textual descriptions varying in wording and structure.
This repo contains my coursework, assignments, and Slides for Natural Language Processing Specialization by deeplearning.ai on Coursera
Reading list of Instruction-tuning. A trend starts from Natrural-Instruction (ACL 2022), FLAN (ICLR 2022) and T0 (ICLR 2022).
SkyChat是一款基于中文GPT-3 api的聊天机器人项目。它可以像chatGPT一样,实现人机聊天、问答、中英文互译、对对联、写古诗等任务。| SkyChat is a Chatbot project based on Chinese GPT3 API. Like chatGPT, it can do human-machine chat, question and answer, and can also complete tasks such as Chinese-English or English-Chinese translation, content continuation, couplets, and Chinese ancient poems writing.
Author: Wenhao Yu (wyu1@nd.edu). ACM Computing Survey'22. Reading list for knowledge-enhanced text generation, with a survey.
Multimodal AI Story Teller, built with Stable Diffusion, GPT, and neural text-to-speech
Code for PaperRobot: Incremental Draft Generation of Scientific Ideas
Compendium of the resources available from top NLP conferences.
A curated list of resources dedicated to Natural Language Generation (NLG)
DialogStudio: Towards Richest and Most Diverse Unified Dataset Collection and Instruction-Aware Models for Conversational AI
REBEL is a seq2seq model that simplifies Relation Extraction (EMNLP 2021).
Tracking the progress in non-autoregressive generation (translation, transcription, etc.)
An NLP system for generating reading comprehension questions
PyTorch Implementation of OpenAI GPT-2
Tracking the progress in end-to-end speech translation
Convert a number to an approximated text expression: from '0.23' to 'less than a quarter'.
Multilingual Generative Pretrained Model
Fine-tuned pre-trained GPT2 for custom topic specific text generation. Such system can be used for Text Augmentation.