Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

NLP Architect by Intel AI Lab

nlp_architect.nervanasys.com

Post reply on HN
Print view View original

11–12 of 12 posts

Re: NLP Architect by Intel AI Lab

#11

Post by ___cs____ »

yorwba wrote: post #8
continuations wrote: post #7

How does this compare to word2vec or fasttext?

word2vec and fasttext are specialized tools for creating word embeddings, this is a more generalist library. It's more comparable to PyText, AllenNLP or Flair, the main difference appearing to be that the other three use PyTorch, not Tensorflow.

with the recent change for TF 2.0. If you would design something similar, will you use TF or Pytorch? What I am trying to ask here is, Is TF 2.0 is comparable to Pytorch when it comes to ease of use?

Re: NLP Architect by Intel AI Lab

#12

Post by m0zg »

___cs____ wrote: post #11
yorwba wrote: post #8

Earlier quoted context omitted.

word2vec and fasttext are specialized tools for creating word embeddings, this is a more generalist library. It's more comparable to PyText, AllenNLP or Flair, the main difference appearing to be that the other three use PyTorch, not Tensorflow.

with the recent change for TF 2.0. If you would design something similar, will you use TF or Pytorch? What I am trying to ask here is, Is TF 2.0 is comparable to Pytorch when it comes to ease of use?

Probably not. It has "imperative" mode, but it also drags in quite a bit of API baggage that PyTorch just doesn't have. It's not that PyTorch is ideal, but its main advantage is it "feels like NumPy". Google also has a library that "feels like NumPy". In fact it kind of _is_ NumPy with hardware acceleration, but it seems to be in very early stages. I heard from insiders that there are only 2 people working on the project, if that. The name of the project is JAX: https://github.com/google/jax. It's arguably a lower level framework on top of which something like PyTorch could be built.
Post reply on HN