Course version

This course outline applies to version 1.0 of AWS Academy Machine Learning for Natural Language Processing (NLP) in English.

Description

AWS Academy Machine Learning for Natural Language Processing (NLP) is a follow-up course to AWS Academy Machine Learning Foundations. The course is at an intermediate technical level (similar to the AWS Academy Architecting, Operations, and Developing courses) and is appropriate for students who are pursuing careers that require machine learning (ML) knowledge.

Curriculum objectives

Upon completion of this course, students will be able to do the following:

• Describe the terms in the NLP ecosystem
• Identify how NLP can be used in business
• Indicate the range of problems, tasks, and solutions with NLP
• Explain the purpose and application of each AWS NLP ML service
• Implement solutions to different NLP problems using AWS ML services
• Run the ML pipeline on AWS for an NLP-specific business problem
• Evaluate various algorithms and approaches for a given NLP problem
• Build a solution using a combination of algorithms and AWS ML services

Duration

Approximately 20 hours. The course is designed to be delivered over one semester. Actual delivery times vary depending on the format. This course must be delivered over a period of at least 4 weeks.

Intended audience

This intermediate (200-level) course is intended for students attending AWS Academy member institutions. The target audience includes learners enrolled in software engineering, data analytics, ML, or IT tracks in a STEM course at a higher education academic institution. Potential learners include undergraduate, graduate, or re-skilling professional learners.

Employment Outcomes

This course is intended for prospective machine learning roles including the following:

• Data engineer
• Data scientist
• Software developer

1      aws.amazon.com/training/awsacademy

© 2021 Amazon Web Services, Inc. or its affiliates. All rights reserved.

Student prerequisites

• Completed the AWS Academy Machine Learning Foundations course
• Familiarity with cloud computing concepts
• Familiarity with Python or similar, higher level programming languages
• Familiarity with general networking concepts
• Familiarity with deep neural networks and graph theory
• Familiarity with bots and how they use utterances and slot prompts

Delivery methods

Learning materials are provided to support any combination of synchronous or asynchronous instructor-led delivery, either in person or online (all modalities).

Educator prerequisites

This course does not have any prerequisites for educators. However, prior to facilitating this course, educators are recommended to complete the AWS Academy Machine Learning Foundations course and this course.

Learning resources

• Video lectures
• Lecture materials
• Instructor Guides
• Student Guides
• Lab exercises
• Sandbox environment for educators

Course timing

This table lists the module timing in this course. Note that the total classroom time for all the modules in this course is 1,200 minutes (20 hours).

Items that are not applicable are marked NA.

Module Title	Lecture (Minutes)	Activity/Lab/ (Minutes)	Knowledge Check (Minutes)	Total Classroom Time (Minutes)
Module 1: Welcome to AWS Academy NLP	50	NA	10	60
Module 2: Introduction to NLP	60	30	10	100
Module 3: Processing Text for NLP	60	90	10	160
Module 4: Implementing Sentiment Analysis	50	30	10	90
Module 5: Introducing Information Extraction	30	120	10	160
Module 6: Introducing Topic Modeling	50	170	10	230
Module 7: Working with Languages	30	30	10	70
Module 8: Course Wrap- Up	10	200	NA	210
Total Course Time	340	670	70	1080

Module sections

This section lists the module sections in this course.

Welcome to AWS Academy NLP

• Course overview
• What is NLP?
• Business problems solved by using NLP
• NLP roles
• Activity: NLP Jobs Scavenger Hunt
• Knowledge check

Module 2: Introduction to NLP

• NLP and ML
• Common NLP tasks
• Walkthrough of an NLP problem

• Lab: Applying ML to an NLP Problem
• Evolution of NLP architectures
• Knowledge check

Module 3: Processing Text for NLP

• Text processing overview
• Getting text
• Lab: Extracting Text from Webpages and Images
• Text preprocessing
• Lab: Processing Text
• Vectorizing text
• Lab: Encoding and Vectorizing Text
• Advanced processing
• Storing and visualizing unstructured data
• Knowledge check

Module 4: Implementing Sentiment Analysis

• Introducing the scenario
• Identifying the steps for text processing
• Examining the algorithms for sentiment analysis
• Lab: Implementing Sentiment Analysis
• Discussing and walking through the lab solution
• Knowledge check

Module 5: Introducing Information Extraction

• Information extraction overview
• Types of information extraction
• Implementing information extraction
• Lab: Implementing Information Extraction
• Lab: Working with Entities
• Knowledge check

Module 6: Introducing Topic Modeling

• Introduction to topic modeling
• Identifying the approach
• Implementing topic modeling
• Lab: Implementing Topic Modeling with Amazon Comprehend
• Lab: Implementing Topic Modeling with Neural Topic Model (NTM)
• Lab: Implementing Topic Modeling
• Knowledge check

Module 7: Working with Languages

• Working with language issues
• Detecting and translating languages
• Transcribing and vocalizing text with AWS services
• Lab: Implementing a Multilingual Solution
• Knowledge check

Module 8: Course Wrap-Up

• Lab: Capstone Project
• Course summary
• Bridging to certification