Hacker News Reader

Comment by wyldfire | Hacker News Reader

I wonder -- there's lots of machine learning designed for making inferences and there's some for language and transfer. How easy is it to train an oracle that you can ask questions? Or could you make an ontology? Seems like a wealth of scientific papers might be a neat thing to train on. Not to emit gibberish new papers, but to make something useful. Somehow.

View on HN

check out our work in this area: https://scite.ai/search/citations

We have extracted 918M citation statements from 27M full text articles.

This is interesting but AFAICT it is "merely" indexing.

So far as I understand it's a lot more than that. Their model has not only indexed but has also individually classified 900M+ citation statements by sentiment, the outputs of which produce a score to represent each paper's relative trustworthiness.

To your point though it's fun to think about generative applications too. I for one would appreciate a writing assistant trained on millions of scientific papers -- like OK I'll write that last-minute proposal for you but you better believe it's going to be chock-full of dispensable lexical arcana.

Yes, there is a lot more that goes into it. The details of our indexing are described in detail in a recent paper of ours: https://direct.mit.edu/qss/article/doi/10.1162/qss_a_00146/1...

Back button is a bit broken there, if you want to back out of the login page.

Reply on news.ycombinator.com