May 26, 2019

I think that in many cases this is genuinely useless, but there are some good and even important applications of the process.

An example is health records. Doctors enter short notes in a text editor for a lot of these, and being able to extract information discover symptom associations using information extraction is much faster than manually going over data.

Here's a good presentation that covers some of this (PDF):

https://people.csail.mit.edu/regina/talks/CNLP.pdf