How Might Machines Read?
When we left off last time, we had arrived that the conclusion that, regardless of whether or not we humans draw on our background knowledge to construct accurate models of the entities and events we read about, it is essential to their purpose that reading machines do so.
The question is: what sort of models will serve this purpose?
Take, for instance, the case of the knowledge structure known as the “script” — essentially, a set of rules governing a stereotypical situation, such as, for example, going to a restaurant.
Roger Schank and colleagues began promoting…
Last time, we were looking at what goes on inside our heads as we read a text, in hopes it might shed some light on how to emulate human reading abilities in an automated knowledge-acquisition system. More specifically, we looked at whether, and to what extent, readers actively construct and manipulate mental models of the entities and events they encounter in the text, versus whether they are content to simply skim over, without reflecting on, the words on the page.
If true, the latter alternative would certainly be far simpler to automate, but is it (true, that is)?
Florinda: [Zorro] made a complete fool out of Esteban. Ha, ha!
Don Diego: Well, with Esteban, there is so much material to work with!
— Zorro, the Gay Blade
Last time, we looked at the handling and mishandling of the atomic units of writing — words. Here we’ll be shifting our focus to the molecular level— to the broader-gauge phenomena of grammar and, more particularly, ungrammaticality as exemplified once again in the works of blockbuster monger Dan Brown. And, as you’ll soon see, there’s lots of material to work with here, too.
As before, our wellsprings of misexamples will be:
Do stories exist only in our heads?
Put the question another way: Is it possible that the overt story — the text physically presented to us on parchment or computer screen — is really only a string of cues intended to guide the reader in reconstructing the full narrative? The answer will have implications for the likelihood of success in such perennial artificial intelligence pursuits as the automated acquisition of knowledge from textual corpora.
In these days of fear and trembling over the imminence of AI apocalypse on the one hand, and joyous expectation of the technological Rapture of a…
If you hadn’t tumbled to it already, this section on The Basics represents something of a departure from the earlier, intensely personal tone and substance of the Introductory blogisodes. I’ll get back into that mode soon enough, I promise, but this magical mystery tour through the basics of English vocabulary, grammar, style, and usage seems to call for a more detached, objective treatment.
And what better place to start than with that most basic of Basics, that old sine qua non of language itself …
In the effort to follow The Accidental Author’s corollary to Heinlein’s First Rule of Writing…
Well, since this blog is supposed to be about writing, I’d better start, uh, writing. And given I’m writing about writing, there’s probably no better place to start than with Robert A. Heinlein’s first two rules of writing from his essay “On the Writing of Speculative Fiction” (Of Worlds Beyond, 1947). They are:
1. You must write
2. You must finish what you write.
Sound advice which, as you’ll know from some of my previous postings, I’ve not always had the easiest time following. That Rule number 2’s a killer.
Sound as the Rules are, though, the list could use…
Having finally put paid to this interminable intro, I thought it only fair to give you some idea what’s headed your way next. In the ensuing weeks (and months (and — who knows? — maybe even millennia)), yours truly, the Accidental Author, will be giving my (admittedly idiosyncratic) take on such topics as —
· II: Why is this Mona Lisa Laughing? — the rules of English usage, style, and grammar, as bent, broken, and shoveled over with dirt in the works of Dan Brown;
· III: Location, Location, Location — where’s a good place to set down a story…
This is getting old, right? Bait and switch: I tell you I’m going to tell you why I wrote Singularity, then I get hung up on some digression or side topic. Well, this time I’m going to do it, I swear. Not least because, truth to tell, it’s getting to be a drag. Besides which, the stuff that’s coming is more interesting.
So this is it, the bite-the-bullet blogisode.
I do have to cut in here for just a moment to qualify what I was saying in the last installment, about the purpose of stories being to capture and explore…
Life-Stories … in which I almost get around to telling you what moved me to write Singularity
I know, I know. I’ve been promising to tell the story of how, against all odds and my own better judgment, I took up the cudgels, or the quill, once again and set out to write Singularity. And I will, I swear, though I’ve got to confess I’m finding it surprisingly hard getting around to so doing.
Not to worry, I’ve figured out why. …
Delusions of Competence, or What Made the Accidental Author Think He Could Do This Thing?
I mean, it’s just putting one word after another, right? How hard could that be?
Not the writing as such, maybe, but certainly the rewriting, not to mention the re-re-rewriting.
But I’m getting ahead of myself. Long before things ever reached the point of words on paper, I had an inkling I could do this thing.
It wasn’t utterly unfounded. I’d published a couple of magazine articles (right around the time of the ill-starred Cosmos episode, in fact), and my day-job as a consultant…
The future remains unwritten, but I'm writing as fast as I can!