Live data from Hacker News

Natural Language Processing: The Age of Transformers

blog.scaleway.com

21–26 of 26 posts

Re: Natural Language Processing: The Age of Transformers

#21
post #12

"This spring, the Elon-Musk-founded AI research lab OpenAI made a splash with an AI system that generates text. It can write convincing fake reviews, fake news articles, and even poetry." You can check it out for yourself. https://talktotransformer.com/ Pretty awesome.

Also https://transformer.huggingface.co Disclaimer: built it.

What was most challenging about building it?

Re: Natural Language Processing: The Age of Transformers

#22
post #12

"This spring, the Elon-Musk-founded AI research lab OpenAI made a splash with an AI system that generates text. It can write convincing fake reviews, fake news articles, and even poetry." You can check it out for yourself. https://talktotransformer.com/ Pretty awesome.

2 researchers from the Brown university were able to reproduce the full, and never released GPT-2 model a couple of days ago. They wrote an amazing blog post and released the weights!! Here's the blog with all the details: https://medium.com/@vanya_cohen/opengpt-2-we-replicated-gpt-... For those of you who don't know what GPT-2 is, here's the simplest & fastest way with a bit of humor: https://blog.floydhub.com/gpt2/

They spent $500k doing it (in research credits for compute). Not sure if this is the best way to spend so much money, considering they made no novel contribution to NLP field, and OpenAI would have most likely released it soon anyway.

Re: Natural Language Processing: The Age of Transformers

#23

>Next we shall take a moment to remember the fallen heros, without whom we would not be where we are today. I am, of course, referring to the RNNs - Recurrent Neural Networks, a concept that became almost synonymous with NLP in the deep learning field. XLNet ( https://arxiv.org/abs/1906.08237 ) is in essence a recurrent neural network, using a transformer (which is based on neural networks) which recurrently keeps co…

RNNs are still useful in actual time-dependent sequences like activity detection, self-driving car steering etc. though even those are getting enhanced by using attention; use of RNNs in NLP was more of a necessity as there were no other Deep Learning models capable of delivering some results on arguably sequential nature of NLP (let's say that is a quite imperfect assumption). As attention allows viewing the whole input at once, it's easier for non-linear optimizer to set meaningful weights without getting into recursion, though that comes at massive memory cost (i.e. forget about using 2080Ti for NLP).

Re: Natural Language Processing: The Age of Transformers

#25

Earlier quoted context omitted.

For the lazy: The bridge wasn't quite right. There were small sparks coming off the incomplete sections of material hanging just to the right of the traffic lights. Gary wasn't worried, however. He walked up carefully. "This is it, guys!" A huge explosion rocked the bridge, and a fireball engulfed the entire bridge. "Shit! Shit!" It seemed as though the fire was just blowing out, and the bridges were back in place. G…

It's not just "not bad." It's scary. It makes enough coherent sense from sentence to sentence that I doubt my mom (missing a few marbles) would notice it doesn't make a whole lot of sense. Combine this...some official looking logos and a request for money for a fine. Determining an actual official government or other institutional request is going to get much harder.

I don't see the danger here though; how is this scarier than what a couple guys in Nigeria could concoct to fool your mom? Any English speaker can still put together a much more coherent an official sounding institutional request.

Re: Natural Language Processing: The Age of Transformers

#26
post #10

Conversational AI is much closer than we think. Neural sequence-to-sequence models are successful in domain specific domains. But in the context of chit-chat based dialogue systems, the responses lack humanity. Undoubtedly due to the fact they don't comprehend our world. Transfer learning alleviates some of that awkwardness. If anyone's interested in further experiments on their own. There is now a unified Python fra…

Really? Most of the chatbots in production are rule based systems.

The transformer can also be used at different levels of abstraction, e.g. to do interesting stuff with knowledge graphs. I think the transformer architecture is about to make things very, very interesting.

https://arxiv.org/pdf/1904.02342.pdf

Post reply on HN