Statistics For Data Entry: The Brave New Step

A reader writes:"First there was Dasher, a novel application of statistical theory that lets free texts be written using only a pointing device. Dasher works by predicting the continuations of the text being written, based on what has been written so far; there is a probability associated with each offered continuation and the presentation is designed to make it easier to choose more probable continuations. A big advantage of statistics-based interfaces is that they automatically enforce correctness, because correct strings are more probable than incorrect ones. Now the same approach has been extended to writing maths. Apropos is a Javascript application (it supports IE6 & Firefox) to create mathematical expressions. It represents the math using MathML, the official XML spec for mathematics. It is definitely clunky when compared to Dasher, but better than MS Equation Editor etc. It is interesting to consider if this approach can be extended to other XML vocabularies (for example, a model for HTML that suggests the markup as you go along - a properly trained one will make it harder to create pages with blinking text, loads of images etc.), or to formal languages other than XML (e.g. programming languages). Stochastic modeling can also be used as a basis for speech recognition, with the recognizer using the model to choose a continuation when the speech signal is ambiguous or indistinct."

Comments

Like t9

[xabi]

It seems to be the same concept as t9.

Re:Like t9

[xabi]

More info in the same dasher web site here

Re:Like t9

[a_hofmann]

While the concept is the same, the application goes way further than t9. This is where I see such ideas bound to failure.

t9 is a great technology because the vocabulary used writing SMS is pretty narrow. After entering the first few characters of a word, the contextual information in the dictionary is good enough (most of the times) to suggest the wanted word very fast. t9 is even able to dereive this information without the user specifying the exact characters but rather just one of the 3-4 on any mobile key.

As said this is possible because of the small dictionary of probable words and the good contextual information for characters and their position in words.

Extending this tech (or event better methods) to larger domains makes the problem much harder very fast, by my feeling I would even say that increase to be exponential in the mathematical sense.

There may be a small, well defined set of possible mathematical formulaes, if you divide the things into small enough junks. Saying the same about XML documents or even native language text (beyond the character/word level) is imho foolish.

I would like to stress that such technologies are very important and promising to lower the input barriers for disabled people, as they already work in the same sense for anyone on very limited devices (like mobile keyboards). On the other side I don't think such things to change the way most of the people already put information into their computers.

Old technology

[Inigo Soto]

That is hardly news. Mobile phone interfaces have been offering this kind of interfaces for years. True, they are useful, but nothing new here

It sounds good .. in theory

[Anonymous Coward]

"You appear to be writing a letter, and here's what you're probably going to say..."

Riiiiiiiiight

[$RANDOMLUSER]

"Twas brillig, and the slithy toves
Did gyre and gimble in the wabe:
All mimsy were the borogoves,
And the mome raths outgrabe."

It knew he was going to say that.

More likely, it's going to predict that someone's going to say "Let's circle back and touch base tomorrow".

Why this isn't the same as T9.

[pkhuong]

Having used both dasher and T9, it seems to me that t9 only takes into account the keystrokes entered for each word. It then correlates them to a dictionary. Dasher, on the other hand, is based on markov chains (yes, like those word/text generators), and thus takes into account the last [n] characters. That makes it much more accurate, and, interestingly enough, should make it particularly well-suited to editing programs in most mainstream languages, since they have a lot of noise words and frequently used sequences.

Quick test

[potifar]

MathML was never really intended for writing by hand, and even if Apropos makes it easier, I can't see myself switching from (La-)TeX anytime soon. I can enter extremely complex mathematical expressions at least 20-30 times faster by typing them in TeX than I ever could do clicking around an interface like Apropos.

MathML is a good idea in theory, but until there are good tools for writing and editing MathML, there will be very few people using it (either for publishing or for archival purposes.)

Failures of inattention

[hussar]

As other posters have noted, this sounds a lot like T9, which is used in cell phones for predictive text entry. T9 is a great utility, but it has happened that what I am writing is less predictable or the there is a more often used combination of letters that results from the keys I have hit. If I don't pay attention, I get the wrong word.

I can't help but think of someone entering a mathematical equation and concentrating more on his idea than what is being written to the screen. Due to this inattention, the equation doesn't work, he figures he's just wrong, and spends hours/days to find the point at which the computer put in its prediction and not what he thought he entered. Worst case, he could abandon what would have been a great idea.

Or, imagine this applied to writing computer programs. Say for example, you are writing a program to calculate the correct distance the probe should hold above the atmosphere so it doesn't burn up. Your cube mate distracts you briefly, and...

Dasher and stats rock

[palad1]

I did a quick test run of Dasher instead of RTFA, and as far as I understand, it works by presenting the most statistically-probable letter in the middle of the input area.

So, by dragging a perfectly horizontal line with my mouse cursor, I was able to create the most statistically-probable sentence.

Here goes, for Science:

Kennedy insider&xeathGhed a noviceable. Punt.uetGrance beganic or Central believe t, space ship,' Alice, it is deleasantB.Carzone.That's luJbi

Conspiracy theorists, area51 nuts and cypherpunks are going to be thrilled!

Ahem

[kahei]

A big advantage of statistics-based interfaces is that they automatically enforce correctness, because correct strings are more probable than incorrect ones.

In a rigorous, technical environment, being _usually_ correct is not enough and a statistics-based approach to ensuring correctness is not very useful.

In an informal environment, correctness is not nearly as common as you might hope, so again a statistics-based approach may well not be as good as actually enforcing definite correctness.

Re:correctness?

[r_j_howell]

from the dasher site http://www.inference.phy.cam.ac.uk/djw30/dasher/ :
With version 3, as with version 1.6, every language requires a text file full of natural writing (about 300K or more); a specification of the alphabet of the language is also required.
It wouldn't be hard at all to make it work for English, as opposed to Americanese, all you have to do is train it on text written with your own preferred idiosyncrasies

This approach favors bloated, redundant encodings

[alispguru]

The reason predictive interfaces work is that most encodings have some degree of redundancy in them. English text is about 50% redundant information, in an information-theoretic sense, and anything based on XML is going to be more so.

To see this for yourself, pick a nice big hunk of English text and gzip it. You'll get about 50-60% compression. Now, pick a similar-sized hunk of XML and gzip it - you'll probably get 75% compression or more.

Tools like this make using bloated, redundant encodings more tolerable by automating some of the redundancy away. It's not clear to me that this is a good thing.