From grep to SPLADE: a journey through semantic search
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
saved by
related reading
- Building a web search engine from scratch in two months with 3 billion neural embeddingsblog.wilsonl.in
- Elicit: AI for scientific researchelicit.com
- Semantic Search Without Embeddingssoftwaredoug.com
- Semantic Search - Sentence Transformers documentationsbert.net
- Our AI Research: How We Evaluate Semantic Search Technology | Exa Blogexa.ai
- Fast regex search: indexing text for agent tools · Cursorcursor.com
- Not All Vector Databases Are Made Equal | Towards Data Sciencetowardsdatascience.com
- Elicit: AI for scientific researchelicit.org
- The Business of Extracting Knowledge from Academic Publicationsmarkusstrasser.org
- Introducing SWE-grep and SWE-grep-mini: RL for Multi-Turn, Fast Context Retrieval | Cognitioncognition.ai
- Prism: mapping interpretable concepts and features in a latent space of language | thesephist.comthesephist.com
- Stream of Search (SoS): Learning to Search in Languagearxiv.org