Introduction to Natural Language Processing with Python

on YouTube ↗48m

" summary

Hands-on pipeline that reads the Reuters dataset (74 indexes), builds a 500-word bag of words vocabulary with stop-word filtering and Porter stemming, converts to sparse counts and TF-IDF floats using scikit‑learn/NLTK, trains a multinomial Naive Bayes classifier and evaluates on the held-out split. Demo runs on KataKoda. Result is surprisingly strong baseline accuracy without parameter tuning; main cost is sparse vector storage and feature engineering rather than model complexity.

AI-written summary · about

" chapters (14)

1. 0:00Start
2. 3:33NLP tasks
3. 8:30Turing test
4. 12:06Creative writing
5. 13:35Start simple
6. 13:54Text Classification Task
7. 15:26Reuters Dataset
8. 16:17Feature extractions for Machine Learning
9. 17:28Bag of Words
10. 22:13Sparse vectors
11. 22:50Machine Learning: Training & Validation
12. 24:32Python Natural Language Toolkit (NLTK)
13. 38:55Conclusions
14. 41:27Other text representations

" related talks

• 30mKick-Start your Understanding of Machine Learning with PythonAndreas Buhlmeier · ML Conference 2018 Spring
• 02h 19mWorkshop: Demystifying Natural Language Processing using Python (Scikit-Learn/ Keras)Vaibhav Srivastav · PyCon APAC 2019
• 44mTeaching Computers ABCs: A Quick Intro to Natural Language ProcessingLory Nunez · PyCon APAC 2018
• 01h 39mNatural Language Processing (NLP) in Python - From Zero to HeroKeith Galli · PyCon US 2020
• 31mDeep Learning Techniques for Natural Language ProcessingParis Buttfield-Addison · Developer Summit 2020
• 01h 27mTips, Tricks and Topics in Text AnalysisBhargav Srinivasa Desikan · PyData Los Angeles 2018
• 23mMultilingual Natural Language ProcessingGajendra Deshpande · Conf42 Machine Learning 2021
• 01h 38mNavigating the World of NLP and Text AnalyticsIsrael Odeajo · DSC MENA 2024