Original image
Google Maps

The Australian Town That Invented A Language

Original image
Google Maps

In the outback of Aboriginal Australia, there’s a blink-and-you-miss-it desert town named Lajamanu, sandwiched between Darwin and Alice Springs. There are no paved roads in the alcohol-free community, and only one store, which is restocked by a supply truck once a week; mail gets delivered just twice a week. But half of the town (population: 700) is making headlines for pioneering a new native tongue: Light Warlpiri.

What does Light Warlpiri look like? Something like this: “Nganimpa-ng gen wi-m si-m worm mai aus-ria.” In English, that’s “We also saw worms at my house.” Most verbs in the language draw from English, but tacking on suffixes is straight from traditional Warlpiri, a language that relies on suffixes to denote grammatical meaning since words can be put in any order.

The town’s citizens all speak “strong” Warlpiri, a “highly endangered” language exclusive to some 4000 people. Light Warlpiri, on the other hand—a language that’s a cocktail of Warlpiri, English, and Kriol (a local dialect dating back to the 19th century and based on creole)—whittles its number of native speakers to just 350, and no one who speaks it is older than 35.

Though several words of Light Warlpiri are derived from their English and Kriol counterparts, linguists have determined it’s a new language in its own right. Carmel O’Shannessy, a University of Michigan linguist who has studied Lajamanu for about a decade, mapped a two-part development process from which Light Warlpiri sprung.

The language started at birth—literally. Lajamanu parents would speak in baby talk that combined English, Kriol, and Warlpiri, which youngsters borrowed as its own language, adding twists to verb structure and syntax like creating a tense that stands for “present or past, but not future” (‘nonfuture time’)—an alien tense for both English and Warlpiri.

O’Shannessy’s best guess is that the language emerged in the 1970s and ‘80s, when Aboriginals first started hopping from language to language in conversation. But Light Warlpiri is still new enough that it doesn’t exist in written form—there’s simply no need.

The youth language movement makes sense for the upstart community—Lajamanu’s 2006 census showed that half of the town’s population was younger than 20 years old. By Australian federal government estimate, the number of citizens indigenous to Lajamanu will spike to 650 from about 440 by 2026. And according to Australian linguist Mary Laughren, many of Light Warlpiri’s pioneers are still alive, giving linguists a rare chance to chronicle a language still in development.

It’s a long way from the town’s beginnings. In 1948, Australia’s federal government, worried about overcrowding and droughts in Yuendumu, forced 550 unlucky citizens to up and leave to what would become Lajamanu. Lajamanu’s population vacated for Yuendumu at least twice, only to get sent back.

The last time Lajamanu made international headlines was for a rainstorm of biblical proportions in 2010, when hundreds of spangled perch fell from the sky on the desert town, to which local Christine Balmer said, “I’m thankful that it didn’t rain crocodiles.”

Original image
iStock // Ekaterina Minaeva
Man Buys Two Metric Tons of LEGO Bricks; Sorts Them Via Machine Learning
May 21, 2017
Original image
iStock // Ekaterina Minaeva

Jacques Mattheij made a small, but awesome, mistake. He went on eBay one evening and bid on a bunch of bulk LEGO brick auctions, then went to sleep. Upon waking, he discovered that he was the high bidder on many, and was now the proud owner of two tons of LEGO bricks. (This is about 4400 pounds.) He wrote, "[L]esson 1: if you win almost all bids you are bidding too high."

Mattheij had noticed that bulk, unsorted bricks sell for something like €10/kilogram, whereas sets are roughly €40/kg and rare parts go for up to €100/kg. Much of the value of the bricks is in their sorting. If he could reduce the entropy of these bins of unsorted bricks, he could make a tidy profit. While many people do this work by hand, the problem is enormous—just the kind of challenge for a computer. Mattheij writes:

There are 38000+ shapes and there are 100+ possible shades of color (you can roughly tell how old someone is by asking them what lego colors they remember from their youth).

In the following months, Mattheij built a proof-of-concept sorting system using, of course, LEGO. He broke the problem down into a series of sub-problems (including "feeding LEGO reliably from a hopper is surprisingly hard," one of those facts of nature that will stymie even the best system design). After tinkering with the prototype at length, he expanded the system to a surprisingly complex system of conveyer belts (powered by a home treadmill), various pieces of cabinetry, and "copious quantities of crazy glue."

Here's a video showing the current system running at low speed:

The key part of the system was running the bricks past a camera paired with a computer running a neural net-based image classifier. That allows the computer (when sufficiently trained on brick images) to recognize bricks and thus categorize them by color, shape, or other parameters. Remember that as bricks pass by, they can be in any orientation, can be dirty, can even be stuck to other pieces. So having a flexible software system is key to recognizing—in a fraction of a second—what a given brick is, in order to sort it out. When a match is found, a jet of compressed air pops the piece off the conveyer belt and into a waiting bin.

After much experimentation, Mattheij rewrote the software (several times in fact) to accomplish a variety of basic tasks. At its core, the system takes images from a webcam and feeds them to a neural network to do the classification. Of course, the neural net needs to be "trained" by showing it lots of images, and telling it what those images represent. Mattheij's breakthrough was allowing the machine to effectively train itself, with guidance: Running pieces through allows the system to take its own photos, make a guess, and build on that guess. As long as Mattheij corrects the incorrect guesses, he ends up with a decent (and self-reinforcing) corpus of training data. As the machine continues running, it can rack up more training, allowing it to recognize a broad variety of pieces on the fly.

Here's another video, focusing on how the pieces move on conveyer belts (running at slow speed so puny humans can follow). You can also see the air jets in action:

In an email interview, Mattheij told Mental Floss that the system currently sorts LEGO bricks into more than 50 categories. It can also be run in a color-sorting mode to bin the parts across 12 color groups. (Thus at present you'd likely do a two-pass sort on the bricks: once for shape, then a separate pass for color.) He continues to refine the system, with a focus on making its recognition abilities faster. At some point down the line, he plans to make the software portion open source. You're on your own as far as building conveyer belts, bins, and so forth.

Check out Mattheij's writeup in two parts for more information. It starts with an overview of the story, followed up with a deep dive on the software. He's also tweeting about the project (among other things). And if you look around a bit, you'll find bulk LEGO brick auctions online—it's definitely a thing!

Original image
Name the Author Based on the Character
May 23, 2017
Original image