From grep to SPLADE: a journey through semantic search
blog.elicit.com
From grep to SPLADE: a journey through semantic search
1–10 of 20 posts
Re: From grep to SPLADE: a journey through semantic search
#2There's also HyDE: https://aclanthology.org/2023.acl-long.99/
Re: From grep to SPLADE: a journey through semantic search
#3This feels like a big missing piece at this stage of AIs evolution. I just searched on Amazon for five inch chair casters. They used to have them but don't anymore. But that took me a long time to find out. Instead it just dumped all of the chair casters and let me read the details to find out the hard way that none of them were what I wanted across 10 pages of results. But I've been spoiled by modern chatbots. I want it to read the product copy and figure it out, and just tell me "We don't have any of those. But here are some others you might like..."
It seems inevitable that search boxes will become for prompts rather than just keywords, and become conversational and include the context of previous searches.
Re: From grep to SPLADE: a journey through semantic search
#4There's also HyDE: https://aclanthology.org/2023.acl-long.99/
Server not found. Might try Wayback.
Re: From grep to SPLADE: a journey through semantic search
#5They don't mention BM25, which still outperforms much of semantic search. A fun exercise is to watch the benchmarks of the latest semantic embeddings models and see that they still struggle to match good 'ol BM25.
BM25 uses the relative statistical frequency of words to identify relevant material, along with some adjustments. It doesn't use ML at all, but it works very well, especially for technical content.
SPLADE is capable for some areas but is slow, and often times it doesn't present much of a benefit (or is worse) versus BM25 for technical searches, where specific technical words don't have many synonyms that it would be able to pull.
The best search systems today use a mix of semantic search and BM25 or SPLADE, depending on the type of material and the speed required.
Re: From grep to SPLADE: a journey through semantic search
#6This article is a fancy way of saying "we take keywords and break them down to synonyms", bundling "machine learning", and acting like it's a magical solution. Not to be dreary it's just not exciting.
Re: From grep to SPLADE: a journey through semantic search
#7They don't mention BM25, which still outperforms much of semantic search. A fun exercise is to watch the benchmarks of the latest semantic embeddings models and see that they still struggle to match good 'ol BM25. BM25 uses the relative statistical frequency of words to identify relevant material, along with some adjustments. It doesn't use ML at all, but it works very well, especially for technical content. SPLADE i…
It's worse than Splade https://i.imgur.com/oGliEIg.png
We've tested various hybrid approaches as well, but that's too much to go into in once post.
Re: From grep to SPLADE: a journey through semantic search
#8This article is a fancy way of saying "we take keywords and break them down to synonyms", bundling "machine learning", and acting like it's a magical solution. Not to be dreary it's just not exciting.
Doing that in a way that actually makes search better is hard (and ACS isn't that at all)
Re: From grep to SPLADE: a journey through semantic search
#9Just wanted to share a fun experience I had when visiting Pompeii last month: we were walking around the city (the archeological park, that is) and I wanted to see one of those roman public bathrooms. So I googled "pompeii latrine" and got for search results links for how to find the bathrooms (as in, the guest facilities). I was initially confused as to why such a clear query got me the completely wrong answer, until it hit me that bathroom and latrine are semantically similar, but not in my context.
At least that's my headcanon, who knows. And it seems like the cool preserved latrinae were in herculanum anyway. Still, fun to think about
Re: From grep to SPLADE: a journey through semantic search
#10Just an FYI, SPLADE is licensed as CC BY-NC-SA 4.0, no commercial use.