Visualizing the toxicity in Twitter conversations https://t.co/zGRz9Ipggu pic.twitter.com/UT791W6pD9
— Nathan Yau (@flowingdata) August 22, 2018
Visualizing the toxicity in Twitter conversations https://t.co/zGRz9Ipggu pic.twitter.com/UT791W6pD9
— Nathan Yau (@flowingdata) August 22, 2018
"End to-end goal-oriented question answering systems" #KDD2018 Tutorial [SLIDES] https://t.co/Exn9sloCho - A lot of good #nlp stuff in these 200 slides
— Xavier 🎗🤖🏃 (@xamat) August 22, 2018
Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction
— ML Review (@ml_review) August 21, 2018
Outperforms SoTA encoder-decoder systems, while being conceptually simpler and having fewer parameters.
Githubhttps://t.co/QlSPJJZOFy
ArXivhttps://t.co/JjWpv9saG8 pic.twitter.com/GfTTNVZ54b
Attention Is All You Need, but CNNs and RNNs help.
— hardmaru (@hardmaru) August 20, 2018
CNN: https://t.co/b7UJ5bEDWu
RNN: https://t.co/m0YUVX1ySM
“Building a text classification model with TensorFlow Hub and Estimators” by TensorFlow https://t.co/ZgCYg2fV95 #deeplearning #machinelearning #ml #ai #neuralnetworks #tensorflow
— TensorFlow Best Practices (@TFBestPractices) August 19, 2018
Top-Down Tree Structured Text Generation. https://t.co/4E44PVF5kX pic.twitter.com/79LvEvGOwu
— arxiv (@arxiv_org) August 16, 2018
Text classification with a small dataset? TF Hub to the rescue!
— TensorFlow (@TensorFlow) August 15, 2018
Learn how to use TF Hub’s pre-trained word embeddings in this tutorial by @SRobTweets ↓ https://t.co/7ecjca9VVL
The code for the unsupervised translation system from FAIR, to be published at EMNLP, is now available on GitHub.
— Yann LeCun (@ylecun) August 15, 2018
Paper: https://t.co/Xz2bIY4gJQ
Guillaume Lample, Myle Ott, Alex Conneau,... https://t.co/MoqiAHdjoO
This is a terrific introduction to NLP transfer learning, showing how to match fasttext's results on 4 million Amazon reviews using just 1000 reviews with ULMFit! https://t.co/8jdsLSJOax
— Jeremy Howard (@jeremyphoward) August 14, 2018
How to do NLP classification if you don't have much labeled data? See how the @feedly team uses the ULMFit paper from @seb_ruder @jeremyphoward @fastdotai to classify Amazon reviews, Great performance with only 100 samples :) https://t.co/P1pnyr2s3p
— Peter Martigny (@PeterMartigny) August 14, 2018
Interested in text analysis of the Russian troll tweets dataset released by @FiveThirtyEight? This analysis at @BuzzFeedNews uses #rstats and #tidytext. https://t.co/k1y1Fz0ih0
— Julia Silge (@juliasilge) August 14, 2018
Looking forward to the Fall 2018 version of my class "Machine Translation and Sequence-to-sequence Models": https://t.co/JEJ7Jb1Zs4
— Graham Neubig (@gneubig) August 13, 2018
There are still a few places left, so take a look if you're at CMU! If you're not, I'll be posting materials as the semester progresses.