View profile

NLP News - Poincaré embeddings, trolling trolls, A2C comic, General AI Challenge, heuristics for writing, year of PyTorch, BlazingText, MaskGAN, Moments in Time

Highlights in this edition include: Poincaré embeddings implementation; designing a Google Assistant
January 29 · Issue #15 · View online
NLP News
Highlights in this edition include: Poincaré embeddings implementation; designing a Google Assistant app and an offensive speech detector to troll trolls; a comic intro to Advantage-Actor-Critic (A2C); the General AI Challenge; heuristics for scientific writing; a Year of PyTorch; BlazingText, a fast word2vec; MaskGAN, a new text generation model; and Moments in Time, a new dataset for video understanding.

Tools and implementations
Poincaré Embeddings for Learning Hierarchical Representations
Facebook's research platform for object detection research
Vecmap - A framework to learn bilingual word embedding mappings
Saving memory using gradient-checkpointing
The Full-Stack Guide to Actions for Google Assistant
NLP Hacks: Trolling the trolls using NLP, Intercom and AWS Lambda
Normalizing Flows Tutorial, Part 1: Distributions and Determinants
Intuitive RL: Intro to Advantage-Actor-Critic (A2C)
How to solve 90% of NLP problems: a step-by-step guide
The Future of AI
The Future Computed
General AI Challenge
Generalization in Deep Learning
Lessons from Optics, The Other Deep Learning
The Generalization Mystery: Sharp vs Flat Minima
More articles and blog posts
Demis Hassabis talks about Learning From First Principles at NIPS 2017
How to do machine learning efficiently
Heuristics for Scientific Writing (a Machine Learning Perspective)
On the contribution of neural networks and word embeddings in Natural Language Processing
Transfer learning: leveraging insights from large data sets
PyTorch, a year in....
AI Beat Humans at Reading! Maybe Not
Best Dressed NLP Researchers 2016 and 2017
Scaling Kubernetes to 2,500 Nodes
Using NLP to Spot Metaphors
Industry insights
Google Sells A.I. for Building A.I. (Novices Welcome)
Amazon SageMaker BlazingText: Parallelizing Word2Vec on Multiple CPUs or GPUs
Building Cross-Lingual End-to-End Product Search with Tensorflow
AI2 sets up CTO residency program to link engineers with mentors
Kaggle Learn
Making France’s digital potential work for everyone
Paper picks
MaskGAN: Better Text Generation via Filling in the ______
Deep learning for sentiment analysis
Building a Conversational Agent Overnight with Dialogue Self-Play
Dataset spotlight
Moments in Time Dataset
Chinese Text Project
Did you enjoy this issue?
If you don't want these updates anymore, please unsubscribe here.
If you were forwarded this newsletter and you like it, you can subscribe here.
Powered by Revue