We are very excited to announce our acquisition of @linkfluence, a global leader in Consumer Insights and Social Analytics!
Learn more: https://t.co/16COF8sSG0
Unsupervised Translation of Programming Languages. Feed a model with Python, C++, and Java source code from GitHub, and it automatically learns to translate between the 3 languages in a fully unsupervised way. https://t.co/FpUL886KS7
with @MaLachaux@b_roziere @LowikChanussot
🤗Transformers 2.0💥
State-of-the-art NLP in TensorFlow 2.0/PyTorch
8 architectures
33 trained models
102 lang.
Seamlessly pick the right framework for training, eval, deploy
Train on TPU ⏩ finetune/test in PyTorch ⏩ serve w. TFX
🍒Keras magic: train SOTA model in 10 lines👇
If you want a sneek-peek in @YejinChoinka, @rown and co-workers work on GROVER (a 1.5 billion param GPT-2-like model), check this live tweet 👇
Interesting hints, results, and analysis!
Paper: https://t.co/aJJrrmQjJc
Demo: https://t.co/MDfzlYa1iE
.@linkfluence is hosting the next @ParisNLP meetup this Wednesday ! Our AI Engineer @alexdut_ will be presenting his work on multilingual sentiment analysis and emotion detection on social media data at scale.
#NLP#ai#DeepLearning#BigData
Rethinking floating point for deep learning - Jeff Johnson at FAIR
- proposes non-linear floating point math -- more energy efficient, accurate
- no retraining or quantization before deployment
- Verilog, C++, PyTorch implementations available
https://t.co/0w3IqE1HUZ
Here is an op-for-op @PyTorch re-implementation of @GoogleAI's BERT model by @sanhestpasmoi, @timrault and I.
We made a script to load Google's pre-trained models and it performs about the same as the TF implementation in our tests (see the readme).
Enjoy!
https://t.co/dChmNPGPKO