A seam is a join in fabric. You guys mean to say "It seems" which is like "It appears that".
I don't mean to be a dick, just a friendly correction :)
I don't mean to be a dick, just a friendly correction :)
I am no native speaker and every friendly correction is helpful, of course!
Trouble with spelling correction: It does not understand context and thus lets you run into wrong wording ....
If I was clever enough I could probably fix it; I've heard that phrase based analysis is used for translation. Most homophonic spelling errors seem fixable using automated lexical context analysis.
Seems there is movement in mobile spell-check and word suggestion but not in desktop?
It was based off of Google's NGrams, I think he used 3-grams, and checked to see how frequently a word showed up between the two words next to it.
The problem with that was it required a HUGE amount of data. Like several hundred gigabytes worth of space just to store the 3-grams (compressed down to one instance of each 3-gram coupled with the number of times it showed up in the original dataset).
That said, homophones and homonyms only would make the 3-gram sets smaller, but it would only detect homophones and homonyms being used incorrectly. I could still use a word incorrectly, and if I'm banking on that software to detect my mistakes it wouldn't.
How I envision it is also a learning tool - "can here you" would pop up a "can {here} you [here refers to location, hear to hearing sound; 'can hear you']" allowing the author to click the 'corrected' phrase. At the same time you're learning the distinctions.
Thanks for the input.