←back to thread

CauseNet: Towards a causality graph extracted from the web

(causenet.org)
229 points geetee | 1 comments | 02 Sep 25 05:26 UTC | HN request time: 0.203s | source
Show context
TofuLover ◴[02 Sep 25 07:53 UTC] No.45100241[source]▶
This reminds me of an article I read that was posted on HN only a few days ago: Uncertain<T>[1]. I think that a causality graph like this necessarily needs a concept of uncertainty to preserve nuance. I don't know whether this would be practical in terms of compute, but I'd think combining traditional NLP techniques with LLM analysis may make it so?

[1] https://github.com/mattt/Uncertain

replies(2): >>45100291 #>>45100428 #
1. notrealyme123 ◴[02 Sep 25 08:26 UTC] No.45100428[source]▶
I get some vibes of fuzzy logic from this project.

Currently a lot of people research goes in the direction that there is "data uncertainty" and "measurement uncertainty", or "aleatoric/epistemic" uncertainty.

I foumd this tutorial (but for computer vision ) to be very intuitive and gives a good understanding how to use those concepts in other fields: https://arxiv.org/abs/1703.04977