Policy Indications: A webinar on National Education Policy for Holistic Development  |  Policy Indications: School Education Department's initiatives during COVID-19 pandemic  |  Policy Indications: 'Technology can be an enabler for India to position itself as a global leader'  |  Policy Indications: Apex Committee meeting provides suggestions for finalization of draft STIP 2020  |  Technology Inceptions: CSIR-CCMB’s Dry Swab direct RT-PCR method to detect Covid gets ICMR approval  |  National Edu News: CSIR–AMPR to highglight Traditional Artisans and Crafts Expo at IISF-2020  |  National Edu News: GITA, a catalyst for nurturing innovation & industrial R&D: Minister  |  Parent Interventions: Headaches and online learning  |  Parent Interventions: E-cigarettes can be a ‘gateway’ to conventional cigarette smoking for teens   |  Parent Interventions: Thanksgiving meals for diabetic children  |  Technology Inceptions: Smart Speaker Determines Optimal Timing to Talk​  |  Teacher Insights: Teaching information literacy  |  Education Information: MISTI Global Seed Funds open for proposals after Covid pivot  |  Policy Indications: ‘Spill-over’ effects that improve the wider education system  |  Parent Interventions: Cambridge Dictionary names 'quarantine’ Word of the Year 2020   |  
October 22, 2020 Thursday 06:43:52 PM IST

Translating lost languages using machine learning

Science Innovations

Researchers at MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) recently made major development in translating lost languages using machine learning: a new system that has been shown to be able to automatically decipher a lost language, without needing advanced knowledge of its relation to other languages. They also showed that their system can itself determine relationships between languages, and they used it to corroborate recent scholarship suggesting that the language of Iberian is not actually related to Basque. The team’s ultimate goal is for the system to be able to decipher lost languages that have eluded linguists for decades, using just a few thousand words.

With the new system, the relationship between languages is inferred by the algorithm. The proposed algorithm can assess the proximity between two languages; in fact, when tested on known languages, it can even accurately identify language families. 

Read More: https://news.mit.edu/2020/translating-lost-languages-using-machine-learning-1021


Comments