Tag: tool

Lingvo is a deep learning framework used for sequence modeling tasks like machine translation, speech recognition, and speech synthesis.

Learn more here ↓ https://t.co/15903utKtH

— TensorFlow (@TensorFlow) February 23, 2019

Neat 📦 by @jacobandrewlong w/ nice vignettes!
🧰 "interactions: Comprehensive, User-Friendly Toolkit for Probing Interactions" https://t.co/fF5fLLYvq4 #rstats #dataviz pic.twitter.com/zPePqwOMXw

— Mara Averick (@dataandme) February 19, 2019

Pytorch-bert v0.6 is out with OpenAI's pretrained GPT-2 🦄 small model & the usual accompanying example scripts to use it.

Now... can you guys wait that the ACL deadline has passed to release any crazy new transformer? 😅

Thanks, you are the best! 🥰 pic.twitter.com/Xn06E4fM4c

— Thomas Wolf (@Thom_Wolf) February 18, 2019

Model based imputation was just merged into scikit-learn: https://t.co/S9KitBC2ed

— Andreas Mueller (@amuellerml) February 15, 2019

Neural Pipeline – NN training pipeline based on #PyTorch to accelerate experiments https://t.co/k2YMKLoGnu
- flexible training
- checkpoint management
- metric visualization
- best practices (e.g. learning rate decaying & hard negative mining)
- DVC compatible metric logging pic.twitter.com/IcGE7rePdh

— Alexandr Kalinin (@alxndrkalinin) February 14, 2019

Building a recommendation engine? Microsoft has open sourced a collection of Jupyter Notebooks detailing best practices with machine learning and deep learning: https://t.co/fch69KHfiL

— David Smith (@revodavid) February 14, 2019

Thanks to @amittrathi amazing nbreview GitHub App, I can now painlessly diff notebooks, add comments requesting changes, without even having to check a PR locally. pic.twitter.com/1LDYGXqPnZ

— Sylvain Gugger (@GuggerSylvain) February 13, 2019

PT-BERT 0.5 out💥
Pretty big release w. not 1 but TWO new pretrained models:
-classic: OpenAI's GPT
-brand-new: Transformer-XL by Google/CMU
As always both should be super easy to use

So...BERT now stands for Big-&-Extending-Repository-of-Transformers😅

Happy Transfer Learning! pic.twitter.com/yIdTHHJKKA

— Thomas Wolf (@Thom_Wolf) February 11, 2019

Happy to announce official release of compare-mt, a tool for holistic analysis of language generation systems (MT, summarization, response generation, etc.)! https://t.co/BP1qZzO0cO
This is our "secret weapon" for analyzing our systems and understanding what's going right/wrong. pic.twitter.com/X5n0BusvjT

— Graham Neubig (@gneubig) February 11, 2019

I became the one of the maintainers of #ggplot2-exts, a nice showcase of ggplot2 extension packages📦 by @emaasit. If you notice some must-know extension is not listed here, please send us a PR! #rstats

Gallery: https://t.co/BMl5U7jbor
repo: https://t.co/8qrfXVTNmm pic.twitter.com/D4aSGlcol4

— Hiroaki Yutani (@yutannihilat_en) February 11, 2019

Woo jupyter-boook now has a CLI!

to get started (on *nix):

pip install jupyter-book
jupyter-book create mynewbook --demohttps://t.co/CaPhQGvIgE

— Chris Holdgraf (@choldgraf) February 9, 2019

Wish it were this simple, you are probably better off checking out keyword extraction models like autophrase: https://t.co/UpUazn84lS

— Peter Skomoroch (@peteskomoroch) February 9, 2019