Introduction to NLP
summary
Hands-on notebook work shows actual code and outcomes: a GitHub repo and Binder Jupyter notebooks run regex, nltk tokenization, Porter stemming and WordNet lemmatization, stopword lists, and a custom POS helper because off‑the‑shelf tags mislead lemmatizer. A live spaCy dependency tree prints relations for sentences like "I like to eat apples and bananas." The demo contrasts Porter stemmer (blunt -ing removal) versus POS-aware lemmatization, sketches bag‑of‑words and n‑grams, and names LSTM and transformer models like BERT and ELMo.
AI-written summary · about
chapters (13)
- 0:00Introduction
- 1:05Defining natural language processing
- 6:15NLP everyday uses
- 8:18Text preprocessing
- 13:48Setting up the pre-processing demo
- 28:37Stemming vs lemmatization
- 38:53Stop words removal
- 39:13Parsing techniques
- 43:00Dependency parsing with spaCy
- 53:59Language models overview
- 59:54NLP applications
- 1:02:27NLP challenges and ethics
- 1:07:11Question and answer session
related talks
01h 27mTips, Tricks and Topics in Text Analysis
01h 39mNatural Language Processing (NLP) in Python - From Zero to Hero
39mHOWTO: Teach Python to Read
48mIntroduction to Natural Language Processing with Python
02h 19mWorkshop: Demystifying Natural Language Processing using Python (Scikit-Learn/ Keras)
01h 31mBuilding a ChatBot with Python, NLTK and scikit
01h 31mModern NLP in Python
25mInventing Curriculum using Python and spaCy