A new algorithm automatically decodes any unknown language

Emily St. John Mandel: “In America you are completely alone in the face of danger”

The Arthur C. Clarke winner reconstructs Bernie Madoff's notorious multimillion-dollar scam case in her latest novel, 'The Glass Hotel,' and turns it into a...

Europe resists relaxing measures for fear of a third wave

Restrictions have made it possible to exceed the peak of cases in many countriesThe confinements imposed in Europe in the face of the onslaught...

Without remittances from the United States, Cubans re-float their old system of ‘mules’

Faced with the restrictions imposed by the government of Donald Trump, the island is looking for ways to survive. How do they do?Accustomed...

Germany extends the restrictions until the end of the year, after a record number of deaths

"It is not at all time to say that everything is fine," Merkel said, after the number of deaths caused by the virus reached...

Trump pardons General Flynn, first fallen for the investigations of the Russian plot

The former head of National Security pleaded guilty to having lied to investigators about his contacts with the Russian ambassador in WashingtonDonald Trump has...

Scientists at the Massachusetts Institute of Technology’s Computer Science and Artificial Intelligence Laboratory (MIT CSAIL) have developed an algorithm that can automatically decode a lost language that is no longer understood without knowing its relationship to other languages.

researchers they developed the algorithm in response to the rapid disappearance of human languages, as most languages ​​that once existed are no longer spoken, and half of the remaining languages ​​will perish in the next 100 years.

The new system could help restore lost languages

The algorithm works by capitalizing on the basic principles of historical linguistics, such as the ways in which languages ​​use phonemic alternatives.

These types of patterns are then converted into mathematical determinants, and this allows the model to segment words from an old language and map them to a similar language.

The algorithm can also identify different language families. For example, their method suggested that languages ​​in the Iberian area, for example Spanish, have nothing to do with Basque, thus supporting modern academic studies.

The project was led by Regina Barzilay, an MIT professor who last month won a $ 1 million award from the world’s largest AI association for her pioneering work in drug development and breast cancer screening.

The researcher now wants to expand the field of activity to determine the semantic meaning of words even if we do not know how to read them.

“For example, we can identify any references to people or locations in the document that can then be further investigated in the light of known historical evidence,” Barzilay said in a statement.

“These methods of identifying entities are commonly used in many word processing applications today and are very accurate, but the main research question is whether the task is feasible without training data for the old language.”


Related Articles