Siri: Apparently no local learning

By -
Siri does not appear to be learning anything at all about what I typically ask "her" to do. Although one of my most frequent "targets" for text messages is my wife, today, when I asked Siri to "Send a text to Elen Callahan," it took three attempts before "she" got what I was saying correctly. I also frequently send messages to myself, for instance, if I am driving and get an idea, I email it to myself. But every few attempts, Siri tells me "I don't see a Jean Callahan in your contacts"! And if I have no Internet connection, Siri does not function at all. I am baffled why no aspect of my previous interactions with the software seems to be cached locally.

So what are we to make of Apple's claim here:

"Apple claims that the software adapts to the user's individual preferences over time and personalizes results, and performing tasks such as finding recommendations for nearby restaurants, or getting directions."

The Wikipedia article on Siri (linked above) has no information about the architecture of the software. Any insights?

Comments

  1. Lord8:13 PM

    The entire speech to text conversion operates on their servers so there wouldn't be much to be done without an internet connection. Since it stores two years of past usage, also there presumably, there wouldn't be much to be done locally, especially when the results would require a search or information transfer (upload, download, connect, dial, email, text). It probably doesn't queue requests for later since there is such a high probability of misunderstanding, full interactivity is necessary.

    ReplyDelete
    Replies
    1. gcallah12:50 PM

      "The entire speech to text conversion operates on their servers so there wouldn't be much to be done without an internet connection."

      Yes, I realize it does. That is exactly my complaint. Why not build a two-tier architecture?

      "It probably doesn't queue requests for later..."

      Huh? Who asked for "requests queued for later"?

      Delete
    2. Ken B3:28 PM

      There is no need to cache much locally if the account on the device can be used to identify the stored material on the server. You can just look it up by id. Lord's point is that this is probably the right way to do it, as otherwise there is too much data to send and send and send and send. So local cache loses out to central cache. Air time is pricey.

      The process later bit is this I expect. The software can only learn interactively, by getting you to respond. So there is nothing that can be queued up for later to train the software with. You need person and server together. A local cache to help with training would not be useful if a connection to the mother ship is required anyway. Once we have the connection use the server cache.

      Delete
    3. Lord10:32 PM

      Two tier buys you next to nothing if everything relies on an active internet connection which all those applications quoted do. You could do dictation like Dragon (which also relies on servers) or aural accessibiity or aural listening like Talkler, or queuing. That would be the universe of possibilities for a two tier architecture. Maybe in the future they will predict what you will ask and download it before asking while you have a connection but that is a bit much to ask for.

      Delete
    4. gcallah9:26 AM

      Lord:

      1) I actually use Siri so I know what I would like it to be able to do when it can't connect; and

      2) I've built multi-tier realtime trading apps with layers of caching, so I have some idea of how some local intelligence could help do those things.

      One important thing to note: it is OFTEN the case that one has a network connection but can't get Siri to work: I don't know if the Siri servers are overloaded or what, but this happens a LOT.

      Delete

Post a Comment

Popular posts from this blog

Libertarians, My Libertarians!

By -
Cruel to be kind means that I love you . Because, while I think you are mistaken, your hearts are in the right place -- yes, even you, Silas --  unlike some people . This Breitbart fellow (discussed in the link above), by all appearances, deliberately doctored a video of Shirley Sherrod to make her remarks appear virulently racist, when they had, in fact, the opposite import. I heard that at a recent Austrian conference, some folks were talking about "Callahan's conservative turn." While that description is not entirely inaccurate, I must say that a lot of these people who today call themselves conservative give me the heebie-jeebies.
Read more

"Pre-Galilean" Foolishness

By -
 I am currently reading The Master and His Emissary , which appears to be an excellent book. ("Appears" because I don't know the neuroscience literature well enough to say for sure, yet.) But then on page 186 I find: "Asking cognition, however, to give a perspective on the relationship between cognition and affect is like asking astronomer in the pre-Galilean geocentric world, whether, in his opinion, the sun moves round the earth of the earth around the sun. To ask a question alone would be enough to label one as mad." OK, this is garbage. First of all, it should be pre-Copernican, not pre-Galilean. But much worse is that people have seriously been considering heliocentrism for many centuries before Copernicus. Aristarchus had proposed a heliocentric model in the 4th-century BC. It had generally been considered wrong, but not "mad." (And wrong for scientific reasons: Why, for instance, did we not observe stellar parallax?) And when Copernicus propose...
Read more