📚 Papers & tech blogs by companies sharing their work on data science & machine learning in production.

Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics

This repository contains the code for "Generating Datasets with Pretrained Language Models".

Semantic Text Similarity Dataset Hub

Transformer seq2seq model, program that can build a language translator from parallel corpus

Unsupervised Word Segmentation for Neural Machine Translation and Text Generation

Algorithms and evaluation tools for extreme clustering

Repository for the CODAH dataset

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

A repo to explore different NLP tasks which can be solved using T5

Paraphrase any question with T5 (Text-To-Text Transfer Transformer) - Pretrained model and training script provided

Repository that accompanies "An Evaluation Dataset for Intent Classification and Out-of-Scope Prediction" (EMNLP 2019)

Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.

Codebase for testing whether hidden states of neural networks encode discrete structures.

Code for EMNLP2020 long paper: BERT-Attack: Adversarial Attack Against BERT Using BERT

Curated repository of notes from papers I'm reading, mostly NLP related. Updated regularly.

Shared repository for open-sourced projects from the Google AI Language team.

🏄 Scalable embedding, reasoning, ranking for images and sentences with CLIP

BERT for question answering starting with HotpotQA

🔮 A refreshing functional take on deep learning, compatible with your favorite libraries

TensorFlow Tutorials with YouTube Videos

Accelerated-KAZE Features

open Multiple View Geometry library. Basis for 3D computer vision and Structure from Motion.

A Julia package for data clustering

Mozilla's Localization Platform

Julia artificial neural networks

A browser based code editor