Ask HN: Good books/courses for an up-to-date introduction to NLP? | Hacker News Reader

Ask HN: Good books/courses for an up-to-date introduction to NLP?

18 pointsmnjn2 comments

After reading a lot of blog posts about GPT-3 and GPT-2 and not understanding a whole lot other than the fact that the results are _amazing_, I've been wondering if there are any good resources out there for a beginner (someone who's experienced in general software development but has next to no experience in ML, DL, and NLP) looking to get into NLP.

A lot of the books and posts I've found seem to be dated. Are they still good enough to get started with or are there better options?

View on HN

It depends where you fall between 'wanting to do something with models like GPT-2' and 'wanting to understand where we are at with NLP'.

If it's the first, you should look at HuggingFace, which package transfer learning in a very accessible way to use. But I'd say that's probably too a big leap from no experience at all to that.

I wrote a detailed article on how to get up to speed with NLP - tracing the path I have gone through. My main thing was getting quickly to the point where I could actually use this stuff:

https://towardsdatascience.com/learn-nlp-the-practical-way-b...

I have also started learning NLP this year. Here is what have followed. If you are completely new to deeplearning I would recommend course from https://www.fast.ai. Since it will teach you the concepts in a more practical way and also the next courses will more theory than practical.

For theory on NLP with deeplearning you can follow Stanford course by Christopher Manning.

http://web.stanford.edu/class/cs224n/index.html#coursework

it will give you a good understanding of how deeplearning is used in a certain area of NLP. But remember deeplearning is one of the techniques for solving NLP problems if you are more interested in Understanding NLP then I would recommend the following book.

https://web.stanford.edu/~jurafsky/slp3/ed3book.pdf

Although, Stanford course should give you a great high-level understanding of how GPT models work but if you really need to go under the hood then I would suggest after finishing this course you should learn Unsupervised Learning in DeepLearning.

Reply on news.ycombinator.com