The company says it doesn’t automatically start using new translations picked up from user data. Facebook users may not themselves be very good at translating slang, and they might even try to teach the system false translations. ![]() Trusted by the leading enterprises and companies worldwide, our company helps clients succeed in international markets with quality tools. “A good quantity of parallel Facebook-post-style data would allow much, much better and more colloquial translations,” he says.īut Manning adds that although free, crowdsourced data isn’t perfect. What doesis a leader in the market for professional human translations, software localization, and advanced language services since 2011, with the headquarters in Newark, USA. “I think the Facebook idea is very good,” she says.Ĭhristopher Manning, a professor at Stanford University, agrees. ![]() Google’s system lets people edit its automatic translations, but that text also leans toward the formal, says Inkpen. Most translation systems are trained with collections of business, political, legal, and news documents that have been translated by professionals, but they tend to use formal language. Diana Inkpen, a professor at the University of Ottawa, says that data could provide a unique opportunity to build translation software with a good colloquial touch.
0 Comments
Leave a Reply. |