• 3
• 0
• 0

zhouzhi

Tabular ML

• 3
• 0
• 0

halflife-regression

• 3
• 0
• 0

MAVE

The dataset contains 3 million attribute-value annotations across 1257 unique categories on 2.2 million cleaned Amazon product profiles. It is a la...

• 3
• 0
• 0

yanmtt

Yet Another Neural Machine Translation Toolkit

• 3
• 0
• 0

indic_nlp_library

Resources and tools for Indian language Natural Language Processing

• 2
• 0
• 0

necessity

"Ale is my bear necessity."

• 2
• 0
• 0

mindset

• 2
• 0
• 0

yubin

Japanese Address Munger

• 2
• 0
• 0

word_cloud

A little word cloud generator in Python

• 2
• 0
• 0

Wikicorpus

• 2
• 0
• 0

watercooler

Significant Machine Translation news/gossips...

• 2
• 0
• 0

warmth

WMT data in Python

• 2
• 0
• 0

usaarhat-repo

Hack and Tell @ Saarland University

• 2
• 0
• 0

USAAR-SemEval-2015

USAAR participation in SemEval2015

• 2
• 0
• 0

undreamt

Unsupervised Neural Machine Translation

• 2
• 0
• 0

uchu

Sane interface to DigitalOcean Spaces

• 2
• 0
• 0

tutorials

• 2
• 0
• 0

translation-cloud

Visualizing word translations as clouds.

• 2
• 0
• 0

transformer-xl

• 2
• 0
• 0

TokenizeAnything

A re-implementation of redpony/cdec's tokenize-anything.pl script in python