A team of Microsoft researchers, including one of Indian-origin, has created an Artificial Intelligence (AI)-powered machine system that can translate sentences of news articles from Chinese to English with the same quality and accuracy as humans.

Researchers from the company’s Asia and US labs said their system achieved human parity on a commonly-used test set of news stories — called “newstest2017” — that was released at a conference recently, a blog post said late on Wednesday.

According to Arul Menezes, an IIT-Bombay alumni and Partner Research Manager of Microsoft’s machine translation team, the team set out to prove that its systems could perform about as well as a person when it used a language pair — like Chinese to English — for which there is a lot of data.

“Given the best-case situation as far as data and availability of resources goes, we wanted to find out if we could actually match the performance of a professional human translator,” said Menezes.

To ensure the results were both accurate and at par with what people would have done, the team hired external bilingual human evaluators who compared Microsoft’s results to two independently produced human reference translations.

“Hitting human parity in a machine translation task is a dream that all of us have had. We just did not realise we would be able to hit it so soon,” said Xuedong Huang, Technical Fellow in charge of Microsoft’s speech, natural language and machine translation efforts.

To reach the human parity milestone on this dataset, three research teams in Microsoft’s Beijing and Redmond, Washington, research labs worked together to make the system more accurate.

“Much of our research is really inspired by how we humans do things,” said Tie-Yan Liu, Principal Research Manager with Microsoft Research Asia in Beijing.

The team used dual-learning method. Every time they sent a sentence through the system to be translated from Chinese to English, the research team also translated it back from English to Chinese.

That’s similar to what people might do to make sure that their automated translations were accurate, and it allowed the system to refine and learn from its own mistakes.

Dual learning, which was developed by the Microsoft research team, can also be used to improve results in other AI tasks.

Another method, called deliberation networks, is similar to how people edit and revise their own writing by going through it again and again.

The researchers taught the system to repeat the process of translating the same sentence over and over, gradually refining and improving the response, Microsoft said.