Comments on: iPhone autocorrection error analysis https://brenocon.com/blog/2011/05/iphone-autocorrection-error-analysis/ cognition, language, social systems; statistics, visualization, computation Tue, 25 Nov 2025 13:11:20 +0000 hourly 1 By: הזבל של הרווארד או של אפל? https://brenocon.com/blog/2011/05/iphone-autocorrection-error-analysis/#comment-68144 הזבל של הרווארד או של אפל? Thu, 16 Jun 2011 08:28:31 +0000 http://brenocon.com/blog/?p=960#comment-68144 [...] מעלה על המוקד מנתח בקצרה את בודק האיות של אפל. זה מזכיר לי שלפני כשנה אפל [...]

]]> By: brendano https://brenocon.com/blog/2011/05/iphone-autocorrection-error-analysis/#comment-64614 brendano Mon, 23 May 2011 03:32:48 +0000 http://brenocon.com/blog/?p=960#comment-64614 gaussian model sounds totally awesome!! seriously though, i bet if you train a p(char|intent) model you’ll end up getting a transition model that reconstructs the topology of the keyboard — e.g. take the first two principal components and it might look like a qwerty keyboard. maybe.

ok screw big fancy LMs, the problem is just to look at a small amount of left context

]]> By: Yoav Goldberg https://brenocon.com/blog/2011/05/iphone-autocorrection-error-analysis/#comment-64495 Yoav Goldberg Sat, 21 May 2011 21:31:11 +0000 http://brenocon.com/blog/?p=960#comment-64495 I don’t think they actually need a huge LM. I bet a 4gram letter-level LM could really go a long way.

]]> By: Aria Haghighi https://brenocon.com/blog/2011/05/iphone-autocorrection-error-analysis/#comment-64465 Aria Haghighi Sat, 21 May 2011 13:32:52 +0000 http://brenocon.com/blog/?p=960#comment-64465 I thought the iPhone did do a unigram LM character-by-character and this was modeled along with the coordinates of the touch on the keyboard as an observation modeled as gaussian centered on the letter you ‘intend’ to touch.

The real problem with the iPhone keyboard are (1) It’s not personalized at all. The unigram model is clearly some generic one. (2) As far as I can gather it’s not looking at the past word at all, so you get no-grammatical predictions a lot. I think you want to condition on the last word regardless of what else you do.

]]> By: brendano https://brenocon.com/blog/2011/05/iphone-autocorrection-error-analysis/#comment-64460 brendano Sat, 21 May 2011 12:13:19 +0000 http://brenocon.com/blog/?p=960#comment-64460 Yeah, I bet Apple totally could do this.

]]> By: andrew m https://brenocon.com/blog/2011/05/iphone-autocorrection-error-analysis/#comment-64429 andrew m Sat, 21 May 2011 06:03:39 +0000 http://brenocon.com/blog/?p=960#comment-64429 from a technical standpoint, is there any reason why iphone autocorrect shouldn’t be as good as google autocorrect?
on the most recent stack exchange podcast they talked about this — apparently a good deal of the google autocorrect was built from people typing one thing, realizing they mis-typed, editing, then searching again. google then interprets that as a correction event and records the change. slick.

couldn’t apple just do this times a billion?

]]>