Text Generation and Summarization

About this course

Implement abstractive and extractive summarization with copy mechanisms and content selection. Control text generation with constrained decoding, nucleus sampling, and evaluate with ROUGE, BERTScore, and human judgments.

• 20 lessons
• 2 h
• advanced

What you'll learn

• Differentiate extractive and abstractive summarization paradigms
• Identify typical applications and challenges in modern summarization
• Implement graph-based extractive summarization
• Compare lexical and semantic sentence scoring methods
• Train a sentence classifier for extractive summarization
• Apply clustering and integer linear programming to select sentences

Finishing the course

• 80 knowledge-check questions along the way, so you know the ideas stuck before you move on.
• Watching is free and needs no account. Sign in to save your progress. Pass each lesson's quiz (60%+) to earn the certificate. Each certificate has its own public verification link to share, marked quiz-verified.

Created by