Skip to main content

Can Artificial Intelligence Decipher Lost Languages? Researchers Attempt to Decode 3500-Year-Old Ancient Languages

Image by Olaf Tausch via Wikimedia Commons

We may not see warp drives any time soon, but another piece of Star Trek tech, the universal translator, maybe become a reality in our lifetime, if it hasn’t already. Machine learning “has proven to be very competent” when it comes to translation, “so much so that the CEO of one of the world’s largest employers of human translators has warned that many of them should be facing up the stark reality of losing their job to a machine,” writes Bernard Marr at Forbes.

But the fact that AI can do things humans do doesn't mean that it does those things well. One Google researcher put the case plainly in an interview with Wired: “People naively believe that if you take deep learning and… 1,000 times more data, a neural net will be able to do anything a human being can do, but that’s just not true.” AI translators have advanced significantly in the past few years, with Google’s Translatotron prototype (yes, that’s its real name), promising to interpret “tone and cadence.” Still, AI translations are often stilted, awkward, and occasionally incomprehensible approximations that no human would come up with.

Does AI’s limitations with living language hinder its ability to decipher very long dead ones, whose orthography, grammar, and syntax has been completely lost? Yuan Cao from Google’s AI lab and Jiaming Luo and Regina Barzilay from MIT put machine learning to the test when they developed a “system capable of deciphering lost languages.” They took a very different approach “from the standard machine translation techniques,” reports the MIT Technology Review, using less data instead of more, a technique they call "minimum-cost flow."

The researchers tested their translation machine on both the 3500-year-old Linear B and Ugaritic, an ancient form of Hebrew, both of which have already been deciphered by people. Still, the AI was “able to translate both languages with remarkable accuracy,” with a rate of 67.3% in the translation of cognates in Linear B. The far older Bronze Age Minoan script Linear A, however (see it at the top), “one of the earliest forms of writing ever discovered… is conspicuous for its absence.” No human has yet been able to decipher it.

A lost language translator machine that only works on languages that have already been translated (it needs preexisting data on the progenitor language to function) may not seem particularly useful. Then again, it could be one step in the direction of what the authors call the “automatic decipherment of lost languages," those that humans can’t already work out on their own. Read the paper “Neural Decipherment via Minimum-Cost Flow: From Ugaritic to Linear B” at arXiv.

via MIT Technology Review

Related Content:  

Artificial Intelligence May Have Cracked the Code of the Voynich Manuscript: Has Modern Technology Finally Solved a Medieval Mystery?

Artificial Intelligence for Everyone: An Introductory Course from Andrew Ng, the Co-Founder of Coursera

Artificial Intelligence Identifies the Six Main Arcs in Storytelling: Welcome to the Brave New World of Literary Criticism

Josh Jones is a writer and musician based in Durham, NC. Follow him at @jdmagness

Can Artificial Intelligence Decipher Lost Languages? Researchers Attempt to Decode 3500-Year-Old Ancient Languages is a post from: Open Culture. Follow us on Facebook, Twitter, and Google Plus, or get our Daily Email. And don't miss our big collections of Free Online Courses, Free Online Movies, Free eBooksFree Audio Books, Free Foreign Language Lessons, and MOOCs.



from Open Culture https://ift.tt/2JJlHCx
via Ilumina

Comments

Popular posts from this blog

Ishkur’s Guide to Electronic Music: An Interactive, Encyclopedic Data Visualization of 120 Years of Electronic Music

In a very short span of time, the descriptor “electronic music” has come to sound as overly broad as “classical.” But where what we (often incorrectly) call classical developed over hundreds of years, electronic music proliferated into hundreds of fractal forms in only decades. A far steeper quality curve may have to do with the ease of its creation, but it’s also a factor of this accelerated evolution. Music made by machines has transformed since its early 20th-century beginnings from obscure avant-garde experiments to massively popular genres of global dance and pop. This proliferation, notes Ishkur—designer of Ishkur’s Guide to Electronic Music —hasn't always been to the good. Take what he calls “trendwhoring,” a phenomenon that spawns dozens of new works and subgenera in short order, though it’s arguable whether many of them should exist. Ishkur, describes this process below in an excerpt from his erudite, sardonic “Frequently Unasked Questions”: If fart noises were sudde...

A 10 Billion Pixel Scan of Vermeer’s Masterpiece Girl with a Pearl Earring: Explore It Online

We admire Johannes Vermeer’s  Girl with a Pearl Earring   for many reasons , not least that it looks exactly like a girl with a pearl earring. Or at least it does from a distance, as the master of light himself no doubt stepped back to confirm countless times during the painting process, at any moment of which he would have been more concerned with the brushstrokes constituting only a small part of the image. But even Vermeer himself could have perceived only so much detail of the painting that would become his masterpiece. https://www.youtube.com/watch?v=cKaZYTwmjwU Now, more than 350 years after its completion, we can get a closer view of Girl with a Pearl Earring  than anyone has before through a newly released  10 billion-pixel panorama . At this resolution, writes Petapixel’s Jason Schneider , we can “see the painting down to the level of 4.4-microns per pixel.” Undertaken by Emilien Leonhardt and Vincent Sabatier of 3D microscope maker Hirox Europe ...

Board Game Ideology — Pretty Much Pop: A Culture Podcast #108

https://podtrac.com/pts/redirect.mp3/traffic.libsyn.com/secure/partiallyexaminedlife/PMP_108_10-7-21.mp3 As board games are becoming increasingly popular with adults, we ask: What’s the relationship between a board game’s mechanics and its narrative? Does the “message” of a board game matter? Your host Mark Linsenmayer is joined by game designer Tommy Maranges , educator Michelle Parrinello-Cason , and ex-philosopher Al Baker to talk about re-skinning games, designing player experiences, play styles, game complexity, and more. Some of the games we mention include Puerto Rico, Monopoly, Settlers of Catan, Sorry, Munchkin, Sushi Go, Welcome To…, Codenames, Pandemic, Occam Horror, Terra Mystica, chess, Ticket to Ride, Splendor, Photosynthesis, Spirit Island, Escape from the Dark Castle, and Wingspan. Some articles that fed our discussion included: “ The Board Games That Ask You to Reenact Colonialism ” by Luke Winkie “ Board Games Are Getting Really, Really Popular ” by Darron Cu...