Some previous discussions,

https://news.ycombinator.com/item?id=16918757

https://news.ycombinator.com/item?id=12453535

https://news.ycombinator.com/item?id=8749518

https://news.ycombinator.com/item?id=7487341

> We need a lot of data to do this well.

Yup. And once you've got a sufficiently large tagged error corpus, spelling correction will be as simple as a lookup: almost all misspellings (in terms of frequency) will be present in the corpus, and you can drop the (rather simplistic) algorithmic part.

But what about “they’re”, “there”, and “their”? And other homonyms people frequently misspell?

By way of word2vec, or ?