A Primer on Neural Network Models for Natural Language Processing (2015)

arxiv.org

134 pointsRobbieStats3 comments

Goldberg also expanded this paper into a book. http://www.morganclaypool.com/doi/abs/10.2200/S00762ED1V01Y2...

It's great to have this all in one place - the change in notation across papers can be quite confusing!

I just wish there was something like this with code examples. It's so frustrating when papers say things like 'we omit biases' and so on because it makes it difficult to reproduce their implementation arghghg.

That's intentional; it's where you spend most of the time and won't be competitive with the authors and their market-ready implementation. However you get to learn cool stuff and can make something better based on it.

Reply on news.ycombinator.com