Ancient Language Processing: Teaching Computers to Read Cuneiform Tablets:
Twenty-five centuries ago, the "paperwork" of Persia's Achaemenid Empire was recorded on clay tablets—tens of thousands of which were discovered in 1933 in modern-day Iran by archaeologists from the University of Chicago's Oriental Institute [(OI)]. For decades, researchers painstakingly studied and translated these ancient documents by hand, but this manual deciphering process is very difficult, slow and prone to errors.
[...]Since the 1990s, scientists have recruited computers to help—with limited success, due to the three-dimensional nature of the tablets and the complexity of the cuneiform characters. But a technological breakthrough at the University of Chicago may finally make automated transcription of these tablets—which reveal rich information about Achaemenid history, society and language—possible, freeing up archaeologists for higher-level analysis.
That's the motivation behind DeepScribe, a collaboration between researchers from the OI and UChicago's Department of Computer Science. With a training set of more than 6,000 annotated images from the Persepolis Fortification Archive, (directed by professor emeritus Matthew W. Stolper), the project will build a model that can "read" as-yet-unanalyzed tablets in the collection, and potentially [create] a tool that archaeologists can adapt to other studies of ancient writing.
"If we could come up with a tool that is flexible and extensible, that can spread to different scripts and time periods, that would really be field-changing," said Susanne Paulus, associate professor of Assyriology.
(Score: 3, Insightful) by bzipitidoo on Monday March 16 2020, @12:06AM (4 children)
It'll be great eventually to have every known cuneiform writing encoded, in UTF-8 most likely. And, expertly translated. Then in the spirit of "those who do not know history are doomed to repeat it", we will know more of what the peeple of those ancient civilizations did and thought, and the mistakes they made.
My personal experience with this sort of thing is discovering that many of the papers of the great 18th century mathematician, Leonhard Euler, are freely available online, in both the original Latin, and in English translations.
Unicode is a great project. In the days of code pages and 40M hard drives, it seemed the plethora of written languages was too much for computers. HELL, WE USED TO PUT UP WITH ALL CAPS, TO SAVE MEMORY.
One other thing about work of this sort is that it weakens the forces of ignorance, and rent-seeking through the sale of hoarded knowledge at extortionate prices, like Elsevier does.
(Score: 2) by takyon on Monday March 16 2020, @12:23AM (3 children)
I like Unicode. There's too much whining about emojis, which are probably winding down anyway.
Getting all of these languages encoded and documents translated will be great practice for when we invent time travel.
[SIG] 10/28/2017: Soylent Upgrade v14 [soylentnews.org]
(Score: 0) by Anonymous Coward on Monday March 16 2020, @02:20PM (2 children)
Unicode is a good concept, it can contain all these emojis because it is so flexible.
Since that flexibility is nearly endless, it might actually last.
I'd love to see Cuniform added to the Unicode standard....
Never mind: https://en.wikipedia.org/wiki/Cuneiform_(Unicode_block) [wikipedia.org]
(Score: 3, Informative) by bzipitidoo on Tuesday March 17 2020, @03:39AM (1 child)
Yep! Unicode will have every widely used written language, ever. Egyptian Hieroglyphs, Minoan Linear A and B, Mayan, Indus Valley .... We don't know how to read Linear A, but it's in there. Mayan and Indus Valley script are not yet in Unicode, but they will be.
(Score: 2) by takyon on Tuesday March 17 2020, @03:48AM
I was wondering if there were any undeciphered scripts included in Unicode. Thanks!
[SIG] 10/28/2017: Soylent Upgrade v14 [soylentnews.org]