For example, if I spell “umportant”, it’s easy for us to recognise that it’s supposed to be “important”, but autocorrect insists that it’s something like “umbrella”, or I guess more logically “unimportant”, even though “important” is only 1 correction away.
​
These are real examples from my phone (Samsung Galaxy):
​
Wuick gets the suggestions Wicked, Which, Wucky, Whickham, Whicker, Wick, Wickets, Wicket, and Wickham. None of which are “Quick”, what I intended to write.
​
Nrown gets the suggestions Now, Nr own, Noon, Nowhere, Nr owner, Nr owns, and Nr owners. None of which are “Brown”.
​
Dence gets the suggestions Dance, December, Denied, Dancers, Decent, Dense, Dench, and Deuce. None of which are “Fence”.
​
It’s bothered me for years that it never ever picks up on a misspelt first letter.
​
Edit: I tried “umportant”, and it actually comes with 0 suggestions. Not umbrella, not unimportant, not even “important”. But “inportant” and “ikportant” and even “iqportant” are all recognised as “important”.
In: Technology
Autocorrect isn’t just correcting misspelled words.
It also takes several other factors into play, but which essentially is one thing: it also predicts what you’re trying to say.
In other words, autocorrect is also informed by autocomplete.
The problem is that autocomplete is pretty much unreliable. If you’ve ever done an autocomplete meme challenge, you know what I’m talking about.
Part of that is training data, which is basically user fault. We sometimes misspell words and we fail to correct them, so the system sees that as a correction and factors that into the whole thing.
Latest Answers