Very cool! I think only using nouns and named entities as nodes is somewhat limiting and in information extraction we can do better, using concept embeddings w/ similarity links for instance. But that might just be an improvement for improvement sake. This looks like solid software engineering groundwork. I will try this on my notes, writing and literature collection and I might put in some fancier NLP.
Looks interesting! Reminds me a bit of how Otter.AI generates Summary Keywords on an uploaded voice recording.
Summary Keywords are really helpful since it is a form of automatic tagging and helps to improve discoverability since easy to see the content of a voice transcription at a glance.
I suggest anyone to try it out using the Otter.AI mobile application which makes the tags visible on the resulting output transcription which is not available when uploading a pre-recorded audio file to the website.
Sorry for the Otter.AI detour, but I think that is my relatable example to the benefit of automatic tagging. I think Otter.AI also uses a form of NLP as well.
Hey HN! A while back I posted about Archivy, a knowledge base I was working on that encouraged archival of online content (https://news.ycombinator.com/item?id=24199419).
I realized that one of the reasons knowledge management is overpowered is that you can create this tapestry of knowledge and ideas compounding off each other, and that's even more true if you integrate it with content from online.
This process is useful but it takes time to link and tag. So I decided to try and see how we could automate it!
Espial creates an auto-generated organization of our knowledge, conceptually and structurally.
This allows you to discover new connections in your ideas and search them based on meaning, not keywords.
The show hn links to the code, but I explain more of Espial's goals here: https://www.uzpg.me/tech/2022/01/31/redefining-pkm-with-nlp
Hope you like it!