The languages that defy auto-translate

The languages that defy auto-translate Seyllou/Getty Images Wolof is a language spoken in Senegal, the Gambia and Mauritania, but is not well served by popular auto-translation tools Imagine you come across a message that could contain life-saving information. Mohammed Elshamy/Getty Images The United Nations produces volumes of translated text every year that can be used to train algorithms "I would say the more interested an individual is in understanding the world, the more one must be able to access data that are not in English," says Carl Rubino, a programme manager at IARPA, the research arm of US intelligence services. "Whenever you study a language, you would never, ever in your lifetime see the amount of data today's machine translation systems use for learning English-to-French translation," says Regina Barzilay, a computer scientist at MIT who is a member of another of the competing teams. But once pre-trained on many languages, the neural models can learn to translate between individual languages using very little bilingual training material, known as parallel data. "These neural network models, they're so powerful, they have memorised a lot of languages, they add words that were not in the source," says Mirella Lapata, a computer scientist at the University of Edinburgh who is developing a summarisation element for one of the teams.