Another submission to IMDb, another response it would be fair to characterise as “robust”:
We first encountered the robot editors of the Internet Movie Database last year, attempting to get an episode summary past its stern battery of automatic parsers. Recently, though, another artificial writing assistant, Grammarly, has come to prominence following a high-profile marketing campaign in which the company attempted to grammar-check EL James’s Fifty Shades Of Grey when the film of the book premiered. It ran James’s text and that of several famous historical authors through the system, and presented its findings in a lively press release.
Grammarly is a hugely ambitious undertaking: an algorithm that attempts to read and parse text like a human editor, and check spellings and punctuation in context. Unfortunately, the marketing push didn’t go as well as might have been hoped. As was widely observed, notably by Jonathon Owen at Arrant Pedantry, the worked examples contained several infelicities or mistakes, including some questionable overpunctuating and a suggestion that The Tempest be corrected to “We are such stuff on which dreams are made on“. As Arrant Pedantry concluded, many of the things Grammarly found in its press release weren’t errors and, where it intervened, “the suggested fixes always worsen the writing”.
The IMDb parser is a much less ambitious undertaking. It doesn’t work on free-form text or purport to “read”: instead, it controls inputs tightly by using step-by-step data entry. And yet somehow, it feels so much more like being edited.
Above all, it’s the tone. As ever, the rejection notice at the top is brisk but not wholly discouraging, like a copy editor intercepting a reporter with a question. Then there’s the fact-checking and the resultant queries, and the automatic corrections for house style (surname, first name), done without a song and dance. Then there’s the institutional memory and the ever-so-slight weariness that goes with it: there are 3,304 attributes like this already – are you sure you want to create a new one? Then there’s the encouragement not to touch the type: “If you don’t understand how the ordering should be formatted, please leave it blank.” And, as we saw last time, it enforces word counts ruthlessly and threatens to reassign material elsewhere if it’s not cut to fit.
Maybe Grammarly wouldn’t have stumbled over the cap ‘W’ in “Written” and asked for guidance; IMDb doesn’t do line-by-line context and only really spellchecks the proper nouns already in its database. But this is big-picture, organisational editing for accuracy and factual consistency. Rather than entering the murky, and often highly debatable, world of comma use and the passive voice, it just aims to get things cross-referred and reliable.
In fact, quite a lot of real editors’ work is like the kind of “database editing” IMDb does. Is that how we normally spell it? Haven’t I read that paragraph somewhere else? Someone else has written a piece about this: what does that say? The parser may not be able to write a headline, but it can certainly keep control of a multi-contributor encyclopaedia.
Assertive, detail-oriented, unbending about style, weary but polite – and, as we see from the “override” tickboxes, stoical about the possibility of being ignored: doesn’t that sound just like an editor? These robots are getting more lifelike by the day.