Modern NLP in Python

on YouTube ↗01h 31m

" summary

Code loads spaCy, gensim and pyLDAvis and runs on the Yelp snapshot of 1 million restaurant reviews to: clean and phrase‑model text, train a 50‑topic LDA (inspectable with pyLDAvis), fit word2vec 100‑dim vectors and project them with t‑SNE. Models run multicore, produce sensible topics (Mexican, sushi, service), useful analogies and dense vocab vectors, and surface issues: non‑English reviews and some entity mislabels. All pipelines are executed and the outputs are saved so the models and visualizations can be reproduced.

AI-written summary · about

" chapters (13)

1. 0:00Introduction
2. 1:07Conference setup
3. 2:11NLP pipeline overview
4. 3:13Yelp dataset prep
5. 10:18spaCy introduction
6. 23:40Phrase modeling with gensim
7. 40:28Topic modeling with LDA
8. 57:59Visualizing LDA models
9. 1:09:10LDA for document description
10. 1:11:39Word vectors with word2vec
11. 1:24:47Word analogies in vectors
12. 1:25:07Visualizing word vectors
13. 1:29:01Q&A

" related talks

• 01h 01mWorkshop: Intro to topic modeling using PythonRussell Martin · Big Data & AI Toronto 2020
• 48mTopic Modelling (and more) with NLP framework GensimBhargav Srinivasa Desikan · PyData Berlin 2017
• 31mDeep Learning Techniques for Natural Language ProcessingParis Buttfield-Addison · Developer Summit 2020
• 46mProcessing Hotel Reviews with PythonMiguel Fernando Cabrera · PyData Berlin 2015
• 01h 39mNatural Language Processing (NLP) in Python - From Zero to HeroKeith Galli · PyCon US 2020
• 21mFrom 0 to a crowd sourced neural network in a jiffyJess Alfredsen, Sebastian Steenssøn · Data Science Conference 5.0
• 01h 51mNatural Language Processing in PythonAlice Zhao · PyOhio 2018
• 01h 14mIntroduction to NLPMariel Frank · PyData New York City 2019