Self-Motivation
David Goggins
Former Navy Seal
Career Development
Bryan Cranston
Actor
Critical Thinking
Liv Boeree
International Poker Champion
Emotional Intelligence
Amaryllis Fox
Former CIA Clandestine Operative
Management
Chris Hadfield
Retired Canadian Astronaut & Author
Learn
from the world's big
thinkers
Start Learning

A.I. is translating messages of long-lost languages

MIT and Google researchers use deep learning to decipher ancient languages.

  • Researchers from MIT and Google Brain discover how to use deep learning to decipher ancient languages.
  • The technique can be used to read languages that died long ago.
  • The method builds on the ability of machines to quickly complete monotonous tasks.


There are about 6,500-7,000 languages currently spoken in the world. But that's less than a quarter of all the languages people spoke over the course of human history. That total number is around 31,000 languages, according to some linguistic estimates. Every time a language is lost, so goes that way of thinking, of relating to the world. The relationships, the poetry of life uniquely described through that language are lost too. But what if you could figure out how to read the dead languages? Researchers from MIT and Google Brain created an AI-based system that can accomplish just that.

While languages change, many of the symbols and how the words and characters are distributed stay relatively constant over time. Because of that, you could attempt to decode a long-lost language if you understood its relationship to a known progenitor language. This insight is what allowed the team which included Jiaming Luo and Regina Barzilay from MIT and Yuan Cao from Google's AI lab to use machine learning to decipher the early Greek language Linear B (from 1400 BC) and a cuneiform Ugaritic (early Hebrew) language that's also over 3,000 years old.

Linear B was previously cracked by a human – in 1953, it was deciphered by Michael Ventris. But this was the first time the language was figured out by a machine.

The approach by the researchers focused on 4 key properties related to the context and alignment of the characters to be deciphered – distributional similarity, monotonic character mapping, structural sparsity and significant cognate overlap.

They trained the AI network to look for these traits, achieving the correct translation of 67.3% of Linear B cognates (word of common origin) into their Greek equivalents.

What AI can potentially do better in such tasks, according to MIT Technology Review, is that it can simply take a brute force approach that would be too exhausting for humans. They can attempt to translate symbols of an unknown alphabet by quickly testing it against symbols from one language after another, running them through everything that is already known.

Next for the scientists? Perhaps the translation of Linear A - the Ancient Greek language that no one has succeeded in deciphering so far.

You can check out their paper "Neural Decipherment via Minimum-Cost Flow: from Ugaritic to Linear B" here.

Noam Chomsky on Language’s Great Mysteries

Noam Chomsky contemplates the basic, yet still unanswerable, questions of linguistics.


Remote learning vs. online instruction: How COVID-19 woke America up to the difference

Educators and administrators must build new supports for faculty and student success in a world where the classroom might become virtual in the blink of an eye.

Credit: Shutterstock
Sponsored by Charles Koch Foundation
  • If you or someone you know is attending school remotely, you are more than likely learning through emergency remote instruction, which is not the same as online learning, write Rich DeMillo and Steve Harmon.
  • Education institutions must properly define and understand the difference between a course that is designed from inception to be taught in an online format and a course that has been rapidly converted to be offered to remote students.
  • In a future involving more online instruction than any of us ever imagined, it will be crucial to meticulously design factors like learner navigation, interactive recordings, feedback loops, exams and office hours in order to maximize learning potential within the virtual environment.
Keep reading Show less

If the Pentagon Is Hiding Aliens from Us, the Zoo Hypothesis May Explain Why

An MIT astronomer famously explained why aliens haven't contacted us yet.

Supporting climate science increases skepticism of out-groups

A study finds people are more influenced by what the other party says than their own. What gives?

Protesters demanding action against climate change

Photo by Chris J Ratcliffe/Getty Images
Politics & Current Affairs
  • A new study has found evidence suggesting that conservative climate skepticism is driven by reactions to liberal support for science.
  • This was determined both by comparing polling data to records of cues given by leaders, and through a survey.
  • The findings could lead to new methods of influencing public opinion.
Keep reading Show less

What is counterfactual thinking?

Can thinking about the past really help us create a better present and future?

Jacob Lund / Shutterstock
Personal Growth
  • There are two types of counterfactual thinking: upward and downward.
  • Both upward and downward counterfactual thinking can be positive impacts on your current outlook - however, upward counterfactual thinking has been linked with depression.
  • While counterfactual thinking is a very normal and natural process, experts suggest the best course is to focus on the present and future and allow counterfactual thinking to act as a motivator when possible.
Keep reading Show less
Scroll down to load more…
Quantcast