Embedded Files
Living and Working with
Modules
Modules
2.1 - Unit Overview: Understanding Language
2.2 - How Computers Understand Language
2.3 - How Intelligent Assistants Understand & Answer
2.4 - Word Embeddings
2.5 - How Computers Represent and Generate Meaning
2.6 - Sentiment Analysis
2.7 - Chatbots
End of Unit Project - Chat GPT Case Study & Research Debate
End of Unit - Feedback
Module Concepts
Module Concepts
Language
Smart Assistants
Learning Objectives
Learning Objectives
List various ways in which they or people around them use language to interact with computers in their daily lives.
Distinguish concepts such as speech recognition, speech generation, and question answering.
Slides
Slides
Teacher Resources
Teacher Resources
Coming Soon!
Student Activities
Student Activities
Case Studies (Slide 12)
Bullying a girl named Alexa- Parents of children called Alexa challenge Amazon
Risk of some features - IS ALEXA SAFE FOR KIDS?
Rude kids?/ privacy concerns? - Are smart speakers really safe for children?
Conversation complexity/Jeopardising teaching professions? - Is Amazon Alexa harmful to children’s educational development?
Wrong/incomplete answers discourage critical thinking - Parents say using Alexa to entertain kids comes with problems
Connections
Connections
Module Concepts
Module Concepts
Sounds and Speech
Waveform and Spectrogram
Audio Pipeline
Learning Objectives
Learning Objectives
Explain what waveforms and spectrograms are.
Explain the components of the human vocal tract.
Give examples of how knowledge is used to disambiguate speech, e.g., disambiguating homophones based on context.
Slides
Slides
Teacher Resources
Teacher Resources
Student Activities
Student Activities
Waveforms & Spectrograms Activity
Software: Spectrogram demo
Teacher's Video Demo support
2. SpeechDemo Activity
Software: SpeechDemo
Teacher's Video Demo support
Speech Video demo (4:30 mins)
Connections
Connections
Module Concepts
Module Concepts
Queries
Parts of speech
Parsing
Semantics
Learning Objectives
Learning Objectives
Explain what a parse tree is, and list some parts of speech.
Describe different types of queries that Google can answer.
Slides
Slides
Teacher Resources
Teacher Resources
Coming soon!
Student Activities
Student Activities
Connections
Connections
Module Concepts
Module Concepts
Semantic dimensions and feature space
Coordinates of a word
Vector arithmetic
Learning Objectives
Learning Objectives
Explain the notion of semantic feature space
Given a semantic feature space, determine where a word should be located in that space
Demonstrate how to solve analogy problems using vector arithmetic
Slides
Slides
Teacher Resources
Teacher Resources
Coming soon!
Student Activities
Student Activities
Connections
Connections
Optional Module 2.5
Optional Module 2.5
Module Concepts
Module Concepts
Machine translation
Capturing meaning
Copy of (T) Module 2.5_ How computers represent and generate meaning.pptxLearning Objectives
Learning Objectives
Explain how computers represent the meaning of language.
Understand that word-at-a-time translation doesn't work. Explain how computers grasp the meaning of entire sentences.
Slides
Slides
Module 2.6 - Sentiment Analysis
Module 2.6 - Sentiment Analysis
Module Concepts
Module Concepts
Sentiment analysis
Copy of T Module 2.6_ Sentiment Analysis.pptxLearning Objectives
Learning Objectives
Explain what sentiment analysis is.
Look at a piece of text and point out words or phrases that will likely lead a sentiment analysis program to conclude that the sentiment is positive or negative.
Slides
Slides
Teacher Resources
Teacher Resources
Coming soon!
Student Activities
Student Activities
Connections
Connections
Module 2.7 - Chatbots
Module 2.7 - Chatbots
Module Concepts
Module Concepts
Chatbots
Constructing bots
Chatbots vs. Assistants
Copy of S Module 2.7 - Chatbots.pptxLearning Objectives
Learning Objectives
Explain how we have conversations with computers, rather than single queries.
Understand the different uses for chat bots and their limitations.
Slides
Slides
Teacher Resources
Teacher Resources
Student Activities
Student Activities
5. Chatbot with BERT Activity
Implement a simple chatbot that represents a character in a story and can answer questions about itself and the story. This activity uses the BERT language model, a transformer neural network that can understand text and answer questions.
Software: ML4K Scratch 3
Note: This is a separate instance from the traditional Scratch hosted by MIT
Optional: Pre-made demo Chatbot with BERT.sb3
6. Intelligent Assistant with Keywords (Cognimates)
Create a simulated intelligent assistant in Scratch using Machine Learning for Kids (ML4K) that responds to voice input, modeled after Siri or Alexa. This is a simulation that outputs predetermined responses to selected keywords in the input; real assistants do much more.
Intelligent Assistant with Keywords (Cognimates) Activity Guide
Software: Cognimates website
Optional: Pre-made demo Intelligent Assistant Cognimates.sb3
Connections
Connections
End of Unit - Feedback
End of Unit - Feedback
Page updated
Google Sites
Report abuse