Conceptarium
paulbricman.com
Conceptarium
1–10 of 10 posts
Re: Conceptarium
#2Corrected internal link: https://paulbricman.com/thoughtware/semantica
Re: Conceptarium
#3I have been working on a knowledge base for things I'm leaning about bike parts. Notes on compatibility, part weights, bookmarks to helpful links, etc
A big challenge I have is when I add a new tag, I'll want to apply it to relevant content I already have. But this takes a long time and until it happens the relevant data can't be retrieved by the tag.
I am curious how the semantic hash is implemented in a conceptarium. If I could focus on adding content and it can drive relationships automatically, that is awesome.
Re: Conceptarium
#4Great write up! Using learned representations for content in personal knowledge bases seems like a huge missing piece of tools like Roam. This appears to go all the way to the other side of the spectrum, not supporting any explicit graph links, IIUC.
I feel like ultimately you want both. Explicit links are a useful navigation affordance with nice properties that spatial embeddings won't give you (e.g. you can explicitly establish a link between things that are not similar according to the embedding space).
More important than that though, explicit links let you train the embedding model to understand the dataset the way the user does. All of these embedding models are trained on graphs (word or sentence cooccurence graphs, parent/child comment graphs on social media, etc.). The graph structure in something like Roam can provide training data for updating and adapting the embedding space to the specific knowledge context in which it's used.
Conversely, if you have an embedding representation of your knowledge base, you can use that to suggest explicit links. The embedding space is the dense dual to the sparse graph of explicit links in something like Roam. It's a fully connected weighted graph rather than a sparse unweighted graph.
Maybe this system is meant to only focus on the spatial embedding representation. That makes a lot of sense. A fully-fledged version of this vision though IMO should include a bridge between these two dual representations.
Re: Conceptarium
#5Semantic similarity clustering seems like a solved problem:
https://paperswithcode.com/sota/semantic-textual-similarity-...
Therefore I have huge doubts in this benchmarck
Re: Conceptarium
#6Great write up! Using learned representations for content in personal knowledge bases seems like a huge missing piece of tools like Roam. This appears to go all the way to the other side of the spectrum, not supporting any explicit graph links, IIUC. I feel like ultimately you want both. Explicit links are a useful navigation affordance with nice properties that spatial embeddings won't give you (e.g. you can explici…
Thanks for the thoughtful bit of commentary! It's true, my disproportionate focus on embeddings and no explicit links might have been just an extreme reaction to the current state of tools for thought which are 99% graph-based. Was curious to see what would happen if you only relied on those. Though I agree that explicit links are sometimes handy and can code useful information, so I'm also excited to see more of this interplay developing in the future.
Re: Conceptarium
#7I have been working on a knowledge base for things I'm leaning about bike parts. Notes on compatibility, part weights, bookmarks to helpful links, etc A big challenge I have is when I add a new tag, I'll want to apply it to relevant content I already have. But this takes a long time and until it happens the relevant data can't be retrieved by the tag. I am curious how the semantic hash is implemented in a conceptariu…
The conceptarium (currently) uses OpenAI's CLIP model which encodes both texts and images into a semantic space so that related items are close to each other. This means that if you have a picture of a bike pump and a written note about bike pumps, then they'll get similar hashes. This means that you can search for written notes on bike pumps by taking a picture of a bike pump (Google Lens style) and also search for pictures using text queries, or a mix.
And oh man a dream of mine as an expat in the Netherlands is to learn how to take my bike apart and put it back together to better understand how it works and how to fix it myself. Though this idea never made it too high in my priorities list.
Re: Conceptarium
#8I'm currently looking into similar ideas with auto-generation of organization in knowledge bases: https://twitter.com/uzpg_/status/1458774952786681856
I plan on releasing something soon, this is super interesting!
Re: Conceptarium
#9I would be very interested to see how the distances between documents that arises out of Conceptarium compares to some user(s) other knowledge graphs they have painstakingly made by hand.
Also, I appreciate the heavy use of Greg Egan novels at the end!
Re: Conceptarium
#10I would be very interested to see how the distances between documents that arises out of Conceptarium compares to some user(s) other knowledge graphs they have painstakingly made by hand. Also, I appreciate the heavy use of Greg Egan novels at the end!
That would be a neat little study for one of those people with a casual Obsidian vault of 80K notes:
1. Randomly pick 2 notes 2. Compute semantic distance and minimum traversal distance through the graph (Linkedin 3rd degree connection style) 3. Get a scatter plot and compute the correlation
If you're one of these knowledge power users ping me by email if you want to collaborate on this!