Teaching Computers ABCs: A Quick Intro to Natural Language Processing
summary
Builds two small apps: an information‑retrieval demo that pulls Wikipedia with Wikimedia + BeautifulSoup, vectorizes with tf-idf + cosine similarity via Gensim and serves results with Flask, and a disaster‑tweet classifier trained on CrowdFlower using Count/TF‑IDF, Truncated SVD and simple logistic regression that scores 78% logistic regression on held‑out data. Describes full ETL→EDA→preprocess→vectorize→evaluate pipeline, compares NLTK, spaCy, Gensim, scikit‑learn and Word2Vec, and stresses unit tests, labeled training data and saving feature vectors for production.
AI-written summary · about
chapters (13)
- 0:00Introduction to NLP
- 1:05Outline and goals
- 1:51Teaching language to humans and computers
- 3:37Use case 1: Information retrieval
- 6:05Use case 2: Disaster tweet classification
- 8:58Understanding embeddings
- 16:23NLP pipeline end-to-end
- 20:19Applying pipeline to Kindred
- 26:25Applying pipeline to tweet triage
- 35:00Q&A: Libraries and tools
- 36:07Q&A: Model development time
- 37:54Q&A: Handling sarcasm and multilingual NLP
- 41:50Q&A: Scaling models to production
related talks
01h 39mNatural Language Processing (NLP) in Python - From Zero to Hero
01h 38mNavigating the World of NLP and Text Analytics
30mKick-Start your Understanding of Machine Learning with Python
35mHow does text become data?
39mHOWTO: Teach Python to Read
31mTaking AI/ML to the next level: Text!
48mIntroduction to Natural Language Processing with Python
02h 19mWorkshop: Demystifying Natural Language Processing using Python (Scikit-Learn/ Keras)