Attention is all you need implementation

A python package for benchmarking interpretability techniques on Transformers.

A goto software for teachers and students.

Training neural models with structured signals.

a bot that generates realistic replies using a combination of pretrained GPT-2 and BERT models

Fast + Non-Autoregressive Grammatical Error Correction using BERT. Code and Pre-trained models for paper "Parallel Iterative Edit Models for Local Sequence Transduction": www.aclweb.org/anthology/D…

⛔ [NOT MAINTAINED] An End-To-End Closed Domain Question Answering System.

SQuAD Question Answering Using BERT, PyTorch

This is the code repo for the paper Type, Then Correct: Intelligent Text Correction Techniques for Mobile Text Entry Using Neural Networks

Code for the paper "Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer"

Neural Text Generation with Unlikelihood Training

Conditional Transformer Language Model for Controllable Generation

🤗 Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Official code and data repository for our ACL 2019 long paper "Generating Question-Answer Hierarchies" (https://arxiv.org/abs/1906.02622).

Resumes generated using the GitHub informations

TensorFlow code and pre-trained models for BERT

Toolkit for Machine Learning, Natural Language Processing, and Text Generation, in TensorFlow. This is part of the CASL project: http://casl-project.ai/

Translate darknet to tensorflow. Load trained weights, retrain/fine-tune using tensorflow, export constant graph def to mobile devices

SLING - A natural language frame semantics parser

A collection of datasets that pair questions with SQL queries.