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 @generativist
Sounds like you got many positive responses, so I guess it's my job to give the negative. Assuming these are academic papers, it seems that sometimes even undergrads cannot extract main questions from closely read text. I'd be sceptical of NPL delivering any deep solution to this
2 replies 0 retweets 3 likes -
Replying to @kaznatcheev
Yea. I want to do so using *explicit* questions — content summarization is too thorny (and beyond my expertise). I think the main problem is that it may introduce bias conditioned by style. I use lots of rhetorical questions; but, lots of people think that's too conversational.
1 reply 0 retweets 1 like -
Replying to @generativist
Do people write explicit questions (i.e. ending in ?-mark) in their papers? I think I only ever write rhetorical or stylistic questions. I definitely don't think the main 'question' of most of my papers could be found by looking for *explicit* questions. Or am I missing goal?
1 reply 0 retweets 2 likes -
Replying to @kaznatcheev
The goals is mostly just, I wonder... But I think the rhetorical / stylistic questions contain a lot of useful information. So, less questions in abstract, more auto-generated hyper-links to similar questions in other works (plus a graph to analyze).
1 reply 0 retweets 1 like -
Replying to @generativist
Ahh, okay. That might be doable then, but I wouldn't know how to interpret the resultant graph.
1 reply 0 retweets 1 like
Analytically, I'm not sure I would either. I think the lowest hanging fruit that may be interesting is a means of navigating it via auto-linking to each section.
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.