Module 2: Embeddings and semantic similarity

AINS6004 — Natural Language Processing

Essential Question

How do vector representations support semantic operations?

Scenario

a product team evaluating an NLP workflow before using it in customer-facing communication

Stakeholders: product manager, support lead, privacy reviewer, and model evaluator

Core Moves

• Define the decision boundary

• Compare baseline and alternative

• Interpret evidence and assumptions

• Identify failure modes

• Recommend next action

Lab & Assignment

Build a simple semantic search over course documents.

Artifact: NLP evaluation packet with task framing, retrieval/evaluation design, and deployment guardrails focused on embeddings and semantic similarity: Build a simple semantic search over course documents.