I have a large repository of PDFs that I've wanted to analyze by constructing a graph over, Similarity of *questions* they ask instead of over, Bibliographical citations. NLP folks, how difficult do you think this task is?
-
Show this thread
-
-
Replying to @residl_deviance @generativist
Depending on how well are "questions" defined, you might get away relatively easily by working at the level of entities. It would be very risky to think about extracting meaning. Anything "embedding"ish will work better over struct.abstracts.
1 reply 0 retweets 1 like
Replying to @athanastasiou @residl_deviance
Thanks!
6:30 AM - 24 Apr 2019
0 replies
0 retweets
0 likes
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.