Summarized top 2018 AI research papers

My 2 favorites are 1. BERT - easy to understand, SOTA results on most NLP tasks, code and pretrained models readily available. What more can you ask! 2. ULMFit - transfer learning for NLP, have been waiting for something like this since a long time.

Both these mean getting better results/models for most NLP tasks with lesser training data, effort and time.

Here is another link explaining these topics in a little more detail (a must read if you are in the NLP field) -- https://jalammar.github.io/illustrated-bert/

My favorite is ULMFiT, although to be fair I'm an author on that paper... ;)

Frankly, all these papers are pretty great. But perhaps the most impressive results are BigGAN (amazing image generation) and BERT (doing things with NLP that I don't think anyone expected to see so soon).