✳flâneur — a map of the web's best reading

From grep to SPLADE: a journey through semantic search

blog.elicit.com · 1,797 words · saved by 2 readers

Almost every app needs search. If you’ve attempted to implement it in your app, you may have discovered that what seems simple on the surface is a deeply challenging technical problem that has kept the brightest minds in computer science busy for decades. In recent years, machine learning has given us semantic search, vastly improving the capability of search. However, the black-box nature of these tools can make them unsuited for some domains, like academic literature review. How can those domains take advantage of better search, while still having reproducible results? This article will take you on a journey to understanding search, including the capabilities and weaknesses of the state of the art in semantic search. A simple string comparison like the unix tool grep is the obvious and naive way to implement search. Of course, we quickly see that it doesn’t get anywhere near the results that users want. It may produce false positives like “car” matching “scar,” and false negatives li

From grep to SPLADE: A Journey Through Semantic Search - Elicit From grep to SPLADE: A Journey Through Semantic Search Adrian "Panda" Smith Member of Technical Staff Engineering Jun 13, 2024 Jun 13, 2024 1 min read Almost every app needs search. If you’ve attempted to implement it in your app, you may have discovered that what seems simple on the surface is a deeply challenging technical problem that has kept the brightest minds in computer science busy for decades. In recent years, machine learning has given us semantic search, vastly improving the capability of search. However, the black-box

Explore this link on the map →

saved by

related reading