jaingaurav3

why_you_should_stop_using_the_roc_curve

transformers

🤗 Transformers: State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch.

rasa

💬 Open source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more - Create chatbots and voice assistants

flair

A very simple framework for state-of-the-art Natural Language Processing (NLP)

nlp-recipes

Natural Language Processing Best Practices & Examples

Generate_True_or_False_OpenAI_GPT2_Sentence_BERT

Generate True or False questions from any content with OpenAI GPT2 text generation, Sentence-BERT semantic search and Berkley constituency parser.

bootstrap-experiments

Experimenting with different bootstrap methods

Generate_MCQ_BERT_Wordnet_Conceptnet

Generate Multiple choice Questions from any content or news article using BERT Extractive Summarization, Wordnet and Conceptnet

curation-corpus

Code for obtaining the Curation Corpus abstractive text summarisation dataset

dataset-distillation-ssnl

Dataset Distillation

sentence-classification

Sentence Classifications with Neural Networks

course-nlp

A Code-First Introduction to NLP course

GANs_for_Credit_Card_Data

Text-Generation-GAN

Generative Advesarial Networks in Text Generation

keras-bert

A simple technique to integrate BERT from tf hub to keras

nlp_overview

📘Overview of Modern Deep Learning Techniques Applied to Natural Language Processing

Lift_curve

Code backing up a Medium post on the Lift Curve

TextGAN-PyTorch

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

stanford-cs-229-machine-learning

VIP cheatsheets for Stanford's CS 229 Machine Learning

alpha-scientist

language-models

pre-trained Language Models

nlp-notebooks

A collection of notebooks for Natural Language Processing from NLP Town

TextDataAugmentation

Code related to experimentation of different Text Data Augmentation Techniques

ODSQA

ODSQA: OPEN-DOMAIN SPOKEN QUESTION ANSWERING DATASET

Focal_Loss_Keras

Multi-class classification with focal loss for imbalanced datasets

BERT_generate_grammar_MCQ_from_news_article

Use pretrained BERT model to automatically generate grammar multiple choice questions (MCQ) from any news article or story.

cookbook-2nd-code

Code of the IPython Cookbook, Second Edition, by Cyrille Rossant, Packt Publishing 2018 [read-only repository]

modeldrift

Capturing model drift and handling its response - Example webinar

Texygen

A text generation benchmarking platform

intro2stats

Introduction to Statistics using Python