M26.2 CONNECT THE MECHANISM
Search learned representations with approximate neighbors
"When do I get my money back?" shares no words with the refunds page. See how vector search finds it anyway, and what the fast index quietly skips.
LESSON OVERVIEW14 min lesson
Lesson overview
"When do I get my money back?" shares no words with the refunds page. See how vector search finds it anyway, and what the fast index quietly skips.
What you’ll explore
- Dense retrieval compares query and document embeddings, often with an approximate index; check similarity, index recall, and real relevance separately.
GO TO THE SOURCE
Original explanations, connected to the research.
Dense Passage Retrieval for Open-Domain Question Answering (Karpukhin et al., 2020)ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT (Khattab & Zaharia, 2020)Efficient and Robust Approximate Nearest Neighbor Search Using Hierarchical Navigable Small World Graphs (Malkov & Yashunin)Introduction to Information Retrieval — authors’ online editionSuggest a correction
A precise note can make an explanation better.
Choose the scene and describe what needs attention. Download a feedback file to share through a channel you already use. This page does not send feedback or connect you with a reviewer.