Classification, extraction, summarization and the evaluation each one needs.
8h · 7 lessons · 1 challenge
Before this: Fine-tuning & Parameter-Efficient Methods
The task-shaped half of NLP: text classification, named entity recognition, extraction into a schema, summarization, and semantic search. Each is paired with its evaluation, because the metrics differ sharply and choosing the wrong one is a common interview stumble.
Ends with a complete pipeline, which is the shape most NLP take-homes take.
A task and four plausible metrics. Choose, then watch a model game the one you picked.
Worth 400 XP.
