Introduction to Language Modeling
summary
Two-part tutorial that starts with n‑gram language model math then walks through a Jupyter hands‑on notebook using the Brown corpus and NLTK to build unigram/ bigram/ trigram models by counting, estimating probabilities, applying Laplace smoothing, generating text (greedy vs. stochastic sampling), and measuring perplexity; includes a Twitter generation challenge with prizes, GitHub notebook links, examples showing how n increases specificity and data changes output, and a brief survey of neural approaches and ethical concerns including GPT‑2 withholding.
AI-written summary · about
chapters (8)
- 0:00Language modeling intro
- 1:52Language model intuition
- 4:48Language model applications
- 9:03Engram language models
- 14:01Build a language model
- 57:30Key takeaways and evaluation
- 1:09:49Language models state and ethics
- 1:14:09Twitter challenge results
related talks
01h 00mInside GPT – Large Language Models Demystified
01h 30mIntroduction to Deep Learning & Natural Language Processing
36mLarge Language Models for Real-World Applications - A Gentle Intro
44mHow to build your own Tiny Language Model from scratch
43mComedy Writing With Small Generative Models
51mLarge Language Models for Real-World Applications - A Gentle Intro
50mGenerative language models
01h 34mA Practical Starter's Guide to building LLM based projects