Rank a retrieval baseline
Retrieval means finding the few documents that can answer a question, out of many. The simplest way is to count shared words: a document that contains more of the question's words is probably more relevant. This shared-word ranking misses synonyms, but it is cheap, easy to inspect, and gives you a score to beat. Build it first. Only then can you tell whether a search by meaning, with embeddings, does better.
About this lesson
Words to know
- retrieval
- Finding the few documents, out of many, that can help answer a question.
- baseline
- The simplest working version, measured first, so that every later change can be compared with it.
- lexical search
- Search that matches the words themselves, not their meaning. It finds
caronly where the text sayscar. - embedding
- A vector that a trained model produces for a piece of text. Texts with similar meaning get vectors that point in similar directions.
Why it matters
This is the search step of a document assistant. The first portfolio project starts from this ranking, measures it, and only then tries embeddings against the same questions.
With a year
How it works, a worked example, the exercise with its tests, three hints and the explained solution are in the app, with a year of Algo150 for $19. The first chapter, Model foundations, is free for everyone: start with Vector dot product.