Summarized top 2018 AI research papers
topbots.com
Summarized top 2018 AI research papers
1–6 of 6 posts
Re: Summarized top 2018 AI research papers
#2If any of you read these, which one is your favorite?
Re: Summarized top 2018 AI research papers
#3If any of you read these, which one is your favorite?
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/
Re: Summarized top 2018 AI research papers
#4If any of you read these, which one is your favorite?
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…
BERT is pretty awesome. Thanks for the link I wasn't aware of it.
Re: Summarized top 2018 AI research papers
#5If any of you read these, which one is your favorite?
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).
Re: Summarized top 2018 AI research papers
#6If any of you read these, which one is your favorite?
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).
Sure, all the papers are one of the best in their respective fields, no doubt about that.
Regarding your paper, do you think similar fine timing techniques can be applied to other NLP tasks like NER? Did you get a chance to try on any other non classification task?
Btw, kudos to you guys for such a practically useful paper.