AI-accelerated Product Development
...
BOOK_CHAPTER
Introduction to language model
Covers:
theory
of
Introduction to N-gram
Estimated time needed:
5 minutes
Questions this item adddesses:
What is a language model?
How to use this item?
This is chapter 3 of the book. Read page 1 and 2.
URL:
https://web.stanford.edu/~jurafsky/slp3/3.pdf
Author(s) / creator(s) / reference(s)
Daniel Jurafsky
Shortlist
public
Share
Introduction to N-gram model
Luan Nguyen
Total time needed:
~42 minutes
See details (learning objective, target audience, etc)...
Learning Objectives
Provides background information about a type of NLP model called N-gram model.
Potential Use Cases
Allows users to further understand advanced/in-depth N-gram topics.
Target Audience
BEGINNER
Data scientists who are new to NLP
Go through the following
annotated items
in order
:
BOOK_CHAPTER
1. Introduction to language model
What is a language model?
5 minutes
VIDEO
2. Chain rule of prob basic
How to use chain rule to calculate probability of a sequence?
6 minutes
VIDEO
3. Introduction to N-gram model
What is a N-gram model?
4 minutes
VIDEO
4. Estimate N-gram probability
How to estimate the probability of a word in N-gram model?
10 minutes
VIDEO
5. A simple bi-gram text generation model
How to apply Markov assumption to make a bi-gram text generation model?
17 minutes
Concepts Convered
Previewing stream
Natural Language Processing
Upcoming Live Sessions
Videos
Learning Packages
Past Capstones
People
Search for a tag:
Tags list
Recommender Systems
AI Ethics
ML in Neuroscience
ML in Economics
Graph Neural Nets
ML for Time Series
AI Sustainability
ML in Chemistry
Science of Science
ML Interpretability
Computer Vision
ML in Material Science
ML in Cybersecurity
Reinforcement Learning
ML Engineering and Ops
Network Analysis
Careers in ML
IOT and Edge Security
ML in Biology
ML in Health
AI Products
Natural Language Processing
ML in Biochemistry and Drug Discovery
ML in Aerospace
Math and Foundations
Quantum Tech and Quantum Machine Learning
Synthetic Data
ML in Climate Science
Investment in Emerging Tech
ML in Physics
Generative Adversarial Networks
Founders Stream
ML in Marketing