Connect with us

Tech News

AI is helping scholars restore ancient Greek texts on stone tablets – TechCrunch

Published

on

Machine learning and AI may be deployed on such grand tasks as finding exoplanets and creating photorealistic people, but the same techniques also have some surprising applications in academia: DeepMind has created an AI system that helps scholars understand and recreate fragmentary ancient Greek texts on broken stone tablets.

These clay, stone or metal tablets, inscribed as much as 2,700 years ago, are invaluable primary sources for history, literature and anthropology. They’re covered in letters, naturally, but often the millennia have not been kind and there are not just cracks and chips but entire missing pieces that may comprise many symbols.

Such gaps, or lacunae, are sometimes easy to complete: If I wrote “the sp_der caught the fl_,” anyone can tell you that it’s actually “the spider caught the fly.” But what if it were missing many more letters, and in a dead language, to boot? Not so easy to fill in the gaps.

Doing so is a science (and art) called epigraphy, and it involves both intuitive understanding of these texts and others to add context; one can make an educated guess at what was once written based on what has survived elsewhere. But it’s painstaking and difficult work — which is why we give it to grad students, the poor things.

Coming to their rescue is a new system created by DeepMind researchers that they call Pythia, after the oracle at Delphi who translated the divine word of Apollo for the benefit of mortals.

The team first created a “nontrivial” pipeline to convert the world’s largest digital collection of ancient Greek inscriptions into text that a machine learning system could understand. From there it was just a matter of creating an algorithm that accurately guesses sequences of letters — just like you did for the spider and the fly.

PhD students and Pythia were both given ground-truth texts with artificially excised portions. The students got the text right about 57% of the time — which isn’t bad, as restoration of texts is a long and iterative process. Pythia got it right… well, 30% of the time.

But! The correct answer was in its top 20 answers 73% of the time. Admittedly that might not sound so impressive, but you try it and see if you can get it in 20.

The truth is the system isn’t good enough to do this work on its own, but it doesn’t need to. It’s based on the efforts of humans (how else could it be trained on what’s in those gaps?) and it will augment them, not replace them.

Pythia’s suggestions may not be perfectly right on the first try very often, but it could easily help someone struggling with a tricky lacuna by giving them some options to work from. Taking a bit of the cognitive load off these folks may lead to increases in speed and accuracy in taking on remaining unrestored texts.

The paper describing Pythia is available to read here, and some of the software they developed to create it is in this GitHub repository.



Source link

Continue Reading
Click to comment

Leave a Reply

Your email address will not be published.

Tech News

Kia EV6 GT Packs 576 Electric Horses And A Drift Mode

Published

on

You might not associate Kia with performance vehicles, but with 576 horsepower on tap, the new EV6 GT unveiled during Monterey Car Week aims to change that.

Continue Reading

Tech News

This Electronic ‘Skin’ Lacking A Chip Could Be The Future Of Wearables

Published

on

But here’s the exciting part: The electronic skin can also be easily customized with a different kind of ion-sensing membrane that is sensitive to other chemicals like glucose and cortisol in the sweat. “We showed sodium sensing, but if you change the sensing membrane, you could detect any target biomarker,” adds co-author of the paper, Jun Min Suh. 

In 2018, a team from Stanford University also came up with a wearable device that can measure cortisol levels in sweat and analyze stress levels. Additionally, 2021 wearable-centric research from the Ecole Polytechnique Fédérale de Lausanne in France revealed that cortisol can be used as a biomarker for treating conditions like burnout and obesity.

Another critical benefit is that the electronic skin is flexible, which means the comfort aspect has already been taken care of. That’s a huge relief, as sleeping while wearing a smartwatch so that it collects detailed information about heart rate patterns is not the most comfortable experience. Plus, sleep tracking coupled with continuous heart rate monitoring is also quite taxing on the battery life of a smartwatch. 

An electronic skin that can transmit data related to heart rate and changes in the chemistry of sweat without a chip or transmission gear is a truly remarkable step. Work in the domain has been making tremendous process. From the potential for tattoos that monitor health to artificial skin that can heal its own bruises, the possibilities are almost endless. 

Continue Reading

Tech News

TikTok Is Furious About This Dodge Charger EV Feature

Published

on

While the TikTokers present at the event seemed blown away by the new Daytona SRT, their comments sections were not as kind. The vehicle’s exhaust feature was panned by a number of users in the replies, with one of the commenters on Fitrich76’s video simply replying: “We reving [sic] speakers now.” Another TikToker, Justin Hillard, is amongst the crowd predicting the move to electric will backfire on Dodge. He said: “Funny part is they will see the sales go down very quickly. Because no one wants electric. Especially because if everyone has to go electric then.” Caleb Schueng added, “You [sic] can I download the challengers exhaust sound? I wanna put it in my civic.”

Comments on ModdedDetroit’s TikTok followed a similar theme, with one user stating: “Such a sad era we’re going into.” Another user simply said, “we truly are going into dark times,” and one user criticized the vehicle’s figurative lack of soul. A notable portion of the comments section claimed Dodge was going to go out of business, though one user did say the car was better than Ford’s Mach-E.

These are just examples from a couple of accounts, but they do seem to reflect the broader reaction across social media. Influencers attending the events seemed quite complimentary about the new EV, while the majority of their followers tore the concept apart. In several cases, the electric engine sound was likened to the noise Simba from “The Lion King” made when he was trying to roar. You could easily argue that comment sections are the last places you want to look while gauging public opinion, but there’s also a case for saying these are the exact people Dodge was hoping to win over with the Daytona SRT.

Continue Reading

Trending