Thank you.
A very detailed guide to essential best practices for text processing:https://blog.insightdatascience.com/how-to-solve-90-of-nlp-problems-a-step-by-step-guide-fda605278e4e …
-
-
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thank you! Btw. there is also similar in the spirit "Approaching almost any
#nlp problem on#kaggle" notebook by@abhi1thakur Featuring#Keras ;)https://www.kaggle.com/abhishek/approaching-almost-any-nlp-problem-on-kaggle/notebook …Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
This is fantastic, thanks for sharing. How would it be approached as a OCC problem, i.e. trained only on 'disaster' tweets. Autoencoder??
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
Thanks for sharing!
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
-
-
What an infuriatingly naive blog post. Not only does not "solve" anything, it ignores most of the substance of NLP, and of language understanding as a more general problem. These facile oversimplifications do little to promote either NLP research/topics, or functional solutions.
-
I think it was meant to be a quick introduction for engineers on how to approach common text classification problems. The title is obviously clickbait-y, but "infuriatingly naive" is a bit harsh, it's Medium, not arXiv.
- Show replies
New conversation -
-
-
Very good overview! In my experience, step one has always been easier said then done. Especially when finding articles/studies on *specific* topics, then converting them to raw text.
Thanks. Twitter will use this to make your timeline better. UndoUndo
-
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.