Natural Language Processing Best Practices and Examples

Posted by sharatsc on Wednesday December 04, 2019 @11:51PM
from the github.com dept.

https://github.com/microsoft/nlp-recipes

( 5 comments | 149 points | on HN )

Re:Natural Language Processing Best Practices and Examples by scribu on Thursday December 05, 2019 @04:46AM (#21711096)

A more descriptive title would be "How to do NLP using the Microsoft Azure platform".

[ Parent | on HN ]

Re:Natural Language Processing Best Practices and Examples by walterkrankheit on Thursday December 05, 2019 @06:19AM (#21711494)

It seems spaCy is missing as a valid tool in this list. It's one of the best!

[ Parent | on HN ]

Re:Natural Language Processing Best Practices and Examples by topicseed on Thursday December 05, 2019 @08:59AM (#21712287)

spaCy's baked-in Pattern Matcher is a delight to work with once a document is tokenized.

[ Parent | on HN ]

Re:Natural Language Processing Best Practices and Examples by gkolli on Thursday December 05, 2019 @11:52AM (#21713854)

Yes! Used spaCy for a hackathon and it was a delight to work with.

[ Parent | on HN ]

Re:Natural Language Processing Best Practices and Examples by sweezyjeezy on Thursday December 05, 2019 @06:39AM (#21711586)

Pre-trained transformer models are awesome... unless latency is in any way important. I worked for an NLP consultancy and that probably applies to like half of the use cases I worked on - anything that has to be close to real time, anything that has to process a lot of documents, and doesn't have access to 8 GPUs. At that point this guide becomes pretty obsolete.

[ Parent | on HN ]