Apple patent may foretell an end to iPhone autocorrect Tourette's
An Apple patent application just published by the US Patent Office shows that the masterminds of Cupertino have figured out (or hope to figure out) a cunning way to work out what words you're going to tap into your little Jesus mobe before you type it. The US Patent Office has not yet granted the patent, but in accordance with …
This topic is closed for new posts.
Umm
"Current models of predictive text"
Well, SwiftKey doesn't...
Want to build up picture of
My identifiable finger movements.
You really don't want to know that do you?
Here's two fingers I will let you make up your own mind.
What?
You mean just like Swift Key 3 does on Android already?
Genuis.
Re: What?
The patent was filed in 2010 if you actually read the patent. Swiftkey came out in 2010. So it's not like they sat around and saw its popularity grow and decided to patent it.
Even if Apple did develop something quickly and patented it quickly there is still a good chance it was in progress before Swiftkey was released.
Fandroids may be all butthurt about it but the only thing it shows is this idea, like most patents, aren't unique ideas which is a case against software patents as a whole But as long as they allow software patents this is goal two groups worked towards and one clearly got to the patent office before the other so it sucks to be the other guy but that's how it works in many cases.
Re: What?
December 2010, the first beta of swiftkey was release in July 2010...:
http://www.swiftkey.net/2010/07
Re: What?
AIUI Swift Key is a Bayesian predictor based on letter inputs. This is a Bayesian predictor based on the exact places you touch the screen when typing. Neither Apple nor Swift Key invented Bayes' Theorem, AFAIAA, and since the inputs to the algorithm differ they are not the same thing. You may as well say they're all ripping off Paul Graham (A Plan for Spam). He definitely did invent Bayes' Theorem, that's why it's called ... oh, wait.
Re: What?
Indeed. It also generates most idiotic and embarassing word replacements not even remotely related to the texter's intention.
Doesn't SwiftKey on the Android already do this ( and countless others no doubt )? It learns what my writing style is like from allowing it access to my historical texts and it seems to be pretty good at knowing what I am about to type when I start a new message.
If Apple applied for a patent on this in 2010 (read the artical)
Then SwiftKey may have a problem. It's certainly not prior art.
Sigh. something else to be turned off.
Predictive Text is just about the worst thing on a device. Try using Russian names with it on and see what you get. My Wife's name gets totally messed up. She knows when peole send her messages with it in. Android PT gives different resuls on some words from an iPhone PT.
Do not want. Fail.
Re: Sigh. something else to be turned off.
Predictive text on my phone turns my name into "Linux". Not sure if that's creepy or cool...
Re: Sigh. something else to be turned off.
Is you name Linus Torvalds by any chance?
Re: Sigh. something else to be turned off.
> Is you name Linus Torvalds by any chance?
Fortunately not.
Re: Sigh. something else to be turned off.
Tends to have objections to abbreviations too. My phone likes to turn 'ooc' into 'oocyte.'
Disabled
As in I disabled it on my iPhone. Keep meaning to it on my old 3GS (it got factory resetted before I gave it to my other half, and it bugs her lots)
But DYAC's business model is based on the auto-correct features of iOS, if Apple fix it, the site won't be able to generate as many funny sex based things.
Re: Ducking Aunts.
T9 always made me laugh:
kiss, lips, lisp, lipp
veran, tesco
coal, anal, cock, amal...
So... they're building a noise model of the user input
and using that to predict the errors that will be generated?
I've got news for them; main stream spelling checkers right back to the very first do this (generally on one or both of the assumptions that 'the user can spell but can't type' or 'the user can type but can't spell') to derive the best order to present corrections.
I did it myself in a dissertation a couple of years ago investigating better correction for OCR.
"Siri, text my wife, tell her I'll be late"
Text received: "ovulate"
Was a fun night…
Re: "Siri, text my wife, tell her I'll be late"
Always thought this strange. Rather than talk to someone on the phone, you are talking to the phone to send a message. I rarely use the thing for voice at the best of time.
Re: "Siri, text my wife, tell her I'll be late"
I also considered it a strange feature. Perhaps useful to people who spend a heck of a lot of time behind the wheel, but for 99% of people, a gimmick.
Fortunately it doesn't work well in Australia, so most people ignore it.
But my Atrix already does this
Not sure if it's built into Android or something moto added but it has profiled me and presents me with the most likely words I use.
The actual algorythm
1. Start
2. Receive key press events
3. Analyze in real time to detect spelling errors and/or make completion suggestions.
4. Detect? If No the goto 2
5. Select and suggest a suggested correction/completion
6. Done? If No the goto 2
7. End
Re: The actual algorythm
Oops. Missed a step
2a. Buffer key press events, including time stamps, for use to identify and/or rank correction/completion suggestions.
There is other stuff which is basically "save the timing/geometry data".
Been there.
My non-iPhone managed to mangle a chat pose that was typed perfectly. "/me preens you." became "/me breeds you."
Re: Been there.
"chat pose"......."/me preens you."
I see your problem. We're just getting to the stage where computers can recognise English words in context reliably. You're a bit ahead of the game in expecting them to handle complete and utter bleedin' cobblers with any degree of accuracy.
Re: Been there.
The internet has many dialects. The /me would be familiar to any user of IRC, while the reference to preening only makes sense to a particular community. Outside of IRC, it's also acceptable to indicate third-person poses by using * delimiters on each end, while * delimiters on a single word are used for emphesis.
Re: Been there.
Shhh, your Furry is showing.
As if "Suricou Raven" wasn't clue enough.
<--- I believe it's fashionable to say "kill it with fire" here.
Swiftkey? Android Jellybean?
Apple you really are annoying me now.
Re: Swiftkey? Android Jellybean?
You wouldn't be so angry in life over silly things if you read all the facts and saw they filed the patent in 2010 no there's no evil plot to steal swiftkey's idea from them.
Re: Swiftkey? Android Jellybean?
Appologies. I guess I should be more clear on where I vent my annoyance. This is just another case where Apple's patent grabbing little hands find another thing they can patent through careful tweaking of something that practially already exists, then they make a big fanfare about how they have a new tech or whatever and all the fanbois squeal and hop about happy. Siri, I'm looking at you
Swiftkey
Just to add to the messages earlier on - I'd be interested to see what differences there are between what Apple is suggesting and what Android SwiftKey already does. I've been using SwiftKey for ages and it beats the hell out of regular predictive text.
Mike T
poor skills
I'd think it would be better to have people learn how to spell correctly. Some text messages I receive would probably be considered another language, if not an extreme dialect.
Re: poor skills
Done already.
http://www.youtube.com/watch?v=6hcoT6yxFoU
Even within its present algorithm, iOS autocorrect is daft
iOS autocorrect doesn't even keep track of cursor relocations. If one moves the cursor back to manually correct something (typically an autocorrect gone wrong), whatever letters you type IN THE MIDDLE OF AN EXISTING WORD (!) are examined without regard to the context (!) and then autocorrected to the point where several words are deleted or overwritten in the process. What amazes me is that the SW Machine that is Apple fails to notice this sort of glaring bug.
Android - many of my coworkers have Android phones. They seem to have many more horrible SW bugs than does iOS. The high points are good (great even), but it seems to be an ecosystem that lets more serious bugs loose. It's great to have alternatives to meet all needs. I'd love to have an Android phone, but I'm not wanting another monthly bill. Perhaps I'll grab a pure Android tablet (as opposed to PlayBook) when they're on sale. Cheers.
Re: Even within its present algorithm, iOS autocorrect is daft
Check and see if they're running 2.3. The vast preponderance of Android phones currently out there are on it because the carriers and manufacturers refuse to pull their finger out. Around 2.3.4 or so either Google or whomever baked the carrier's custom ROM were screwing around with how text entry worked... It got better in 4.0, or at least with the Nexus reference device it did. Also, see if they have Swype or not. If not, there's the problem right there.
If you want an Android phone, see if you can score the Galaxy Nexus GSM unlocked version? Google just dropped the price on it a bit, pop your sim in it or the iPhone for the day, swap at lunch, etc...
But I love the autocorrect from my mother-in-law
"anal but bags about" - I still have not idea, but I replied yes
Dics too big
The main problem with autocorrect, imho, is that the dictionaries are vastly huger than the optimal size. After about 3 autocorrect muff-ups I swyped 'this is ridiculous' only to end up sending 'this is Tuscaloosa'.
Similar problems with spellcheckers in word-processors or browsers. It's much better to question a new word (with the option to add to the user's personal dictionary) than to consider it a correctly spelt obscure or archaic word. Only crossword-solving dictionaries need to be big.
Re: Dics too big
There's loads of research out there which suggests that the optimal for a spelling correction dictionary is one that contains only the words in the words used in the corpus. There's an obvious issue with that, but the way I do it is to use fairly small (90k words or so) dictionary and analyse the text under correction to identify words which both look as if they are following the same general spelling rules of the language used and which are frequently used.
Re: Dics too big
How do you make the distinction between "obscure" and otherwise? E.g., geomorphology might be an utterly obscure word for say an arts major, while being part of the usual vocabulary of an Earth Sciences graduate.
Swype
Nothing I've used compares to Swype. Really smooth (don't have to lift my finger off the keyboard) and at least twice as fast.
My hovercraft is full of eels
... that'll fool it.
Mind you, if it manages to display 'would have' instead of 'would of' it would be the greatest invention this century.
Does this even work?
There's a genre of disastrous bad texts apparently (if genuine) generated by the device remembering that you used a very rude word before, and you seem to be using it again.
And I don't suppose that if your cockatiel bird is a male, a cock, that the finger movement for the first four letters is different.
Of course they are trying to avoid you sending a word that you didn't intend to write, so it's near-miss typing that's the issue - making the bad letter a smaller target, maybe.
I'm sorry...
but what about making the device able to fold up, revealing a keyboard below? That way you also wouldn't have to use valuable screen space for a virtual keyboard.
This topic is closed for new posts.
