51–60 of 76 posts
I wish all of you not to fall in the trap of ontologies. I worked very hard in this domain my conclusion is that all ontologies fail to scale eventually. I would recommend people in the field to go towards "perspectivism".
Any NLP application directly encoding knowledge (objects, perspectives, whatever) is going to have major scaling constraints, since it's impossible right now to encode human-level understanding automatically.
So this is the ‘semantic web’ from ~15 years ago?
Earlier quoted context omitted.
Recent work suggests it's possible to generate knowledge graphs from large corpi of text encoded with a language model: https://arxiv.org/abs/2010.11967
Similar work (I'm the first author): generating temporal graphs from text using language models https://arxiv.org/pdf/2010.10077.pdf .
Earlier quoted context omitted.
Similar work (I'm the first author): generating temporal graphs from text using language models https://arxiv.org/pdf/2010.10077.pdf .
Cool! I'm an incoming undergrad transfer to CMU this fall interested in graph-based NLP. Mind if I email you in the next couple days?
On a side note, I love the idea of researchers writing “articles” in this format. No paywall, no complex two-column format, no PDFs. As a researcher myself, I wish this is what my “productivity” was judged upon, I’d probably have a lot more fun and motivation to work and produce!
>no complex two-column format, Two columns is for the reader's benefit - your eyes can keep their place on the page much more easily when jumping half the distance to the beginning of the next line
I've created some useful output from Wikidata's dataset with some-space saving decisions like focusing on certain languages and an arbitrary data structure. The dump is quite big and space at a premium.
So this is the ‘semantic web’ from ~15 years ago?
Slightly off-topic, does anyone recommend any open-source ANSI C implementations of knowledge graphs/graph databases? I had toyed around a bit with Neo4J and am interested in something in a language I'm more familiar with. I've created some useful output from Wikidata's dataset with some-space saving decisions like focusing on certain languages and an arbitrary data structure. The dump is quite big and space at a pre…
But I don't know if it scales up to Wikidata size.
Slightly off-topic, does anyone recommend any open-source ANSI C implementations of knowledge graphs/graph databases? I had toyed around a bit with Neo4J and am interested in something in a language I'm more familiar with. I've created some useful output from Wikidata's dataset with some-space saving decisions like focusing on certain languages and an arbitrary data structure. The dump is quite big and space at a pre…