cynthia

kosentences

Large scale unannotated Korean corpus for unsupervised tasks. (e.g. Language modeling)

stylekqc

austsentences

Large scale web corpus of Austronesian text.

CenterNet_Pytorch_1.2

Object detection, 3D detection, and pose estimation using center point detection:

pyflann3

Python bindings for FLANN - Fast Library for Approximate Nearest Neighbors. (With Python 3 compatibility patches)

sse

Simple tool to allow an annotator to look at a source sentence and pick the most similar sentence out of a set of sentences.

ama

An educational experiment.

crosvm

japanese-twitter

kernel

pytudes

Python programs to practice or demonstrate skills.

rainbow-memory

Official pytorch implementation of Rainbow Memory (CVPR 2021)

vissl

VISSL is FAIR's library of extensible, modular and scalable components for SOTA Self-Supervised Learning with images.

AB-public

Advisory Board repository for materials not meant to be restricted to W3C Members

aom

Accessibility Object Model

atom

:atom: The hackable text editor

dams

design-principles

A small-but-growing set of design principles collected by the TAG while reviewing specifications

doc_lm

geofront-cli

It provides a CLI client for Geofront, a simple SSH key management server.

html

Working Draft of the HTML specification

khaiii

Kakao Hangul Analyzer III

KoGPT2

Korean GPT-2 pretrained cased (KoGPT2)

neuralHMM

code for unsupervised learning Neural Hidden Markov Models paper

nlp-resources

Curated list of NLP resources (with a strong focus on CJK languages)

nlp100.github.io

NLP 100 Exercises

OSX-KVM

Run macOS on QEMU/KVM. Only commercial support is available. With OpenCore + Big Sur support now!

pydemux

testSignificanceNLP

tokenization-scorer

Simple-to-use scoring function for arbitrarily tokenized texts.