It's basically a buzzword detector.
"this is just a tool for detecting buzzwords"
=> Bad: 0.9991 - Good: 0.0011
"this is merely a device for detecting artificially sophisticated words"
=> Bad: 0.0019 - Good: 0.9980
"this is just a tool for detecting buzzwords"
=> Bad: 0.9991 - Good: 0.0011
"this is merely a device for detecting artificially sophisticated words"
=> Bad: 0.0019 - Good: 0.9980
=> Good: 0.9986
"linux for sohpisticated when if contextual what but then what"
=> Good: 0.0201
Put another way, I think misspelled titles are well within the problem domain here.
Is it interesting for this project? Based on my skimming of the README, probably not. I don't think it handles misspellings intelligently.
Maybe it's sohpisticated because Linus is going to RIIR?
Bad: 0.0001 - Good: 0.9999
I'm honestly interested - do we hobble our neural networks with our choice of training space? If for instance, the HN-NN-input space including 'prepositions and word-frequency statistics', would the network train for sentence sophistication? Just because those stats were in front of it?
Yes, frequently. It is common in various areas of math -- mathematical background is not something "normal people" usually flaunt, but there are good reasons to expect programmers to have much more such background than average.
A good rule of thumb is that people are probably using the words they use because those words make sense to them. See the first panel here: http://www.basicinstructions.net/basic-instructions/2009/1/2...
Unfortunately far too often both in tech and in CS academia (and I'm talking about informal conversations ie. this is an 'orthogonal idea')