![]() ![]() These new “human parity” engines have been sweeping international competitions of translation quality and, as opposed to a lot of the other entries, these are available in production. They use the trick that so many of us have used to hilarious effect: it translates sentences from English to another language, then translates that translation back to English to see whether it is the same. ![]() They train a separate neural network to detect and correct errors in the input data. For example they use a large deep neural network to train a much faster wide shallow network, gaining a huge performance improvement and improved translation quality. ![]() Microsoft then improved on the size and performance of these complex models, using groundbreaking techniques. These initial engines were not suitable for production, they were far too massive. Mind you this is a controversial claim and neither the humans with whom parity was achieved nor the people doing the rating of translation quality were professional translators, but we use the “HP” label to refer to the technology being used, not necessarily to the quality level. Then in March 2018 Microsoft announced it had achieved “Human Parity” for some translation tasks. For most major languages, the best quality model is using neural translation. It still requires massive amounts of computing power to train such models, something like 100 processors for a week for each training run, but Microsoft is a leader in technologies to use less processing power so it uses a fraction of that. Because of this, neural machine translation technology has progressed quickly. Interestingly, large software companies like Microsoft and Google tend to publish their results and make their insights and tools available to each other, so that they can each improve on one another’s work. These deep networks require enormous amounts of computing power to train. For others there are even higher quality models available.įollowing table shows which languages are currently supported and to whatĪround 2015, based in large part on algorithms developed at the University of Toronto and Université de Montréal, Neural Network models emerged as a better alternative to statistical models. For several languages the best quality available uses these statistical models. This technology got better and better over the years. It trains on large corpora of text that is already translated, trying to mimic the translation process using statistics. This was the state of the art until a few years ago, using syntax-based statistical translation models with a few additional tricks to improve translation quality. The technology that most people are used to, which powered the old Bing and Google translation engines, is statistical machine translation. In the back end, PointFire Power Translator uses one of four different translation technologies, powered by Azure translation technologies. The quality of machine translation can vary by language. However this table is also useful for any project combining SharePoint and Azure text translation. The overlap, where a language is supported by both SharePoint and Azure means documents and SharePoint pages immediately show up in any of those languages. If you are unaware of the PointFire products, PointFire 365 is the one that handles localizing the user interface and filtering content by language, while PointFire Power Translator is the one that carries out machine translation of documents, classic and modern pages and metadata in SharePoint Online and OneDrive. The Azure Translator Text API v3, part of Cognitive Services, supports even more languages, but it is a different list of languages although there is considerable overlap. When a modern Communication or Teams site is created, all 51 languages are activated automatically, as opposed to classic where alternate languages had to be added individually, or on-premise where before that where 50 individual language packs first had to be installed on all the servers in the farm. SharePoint itself supports 51 languages, as does PointFire 365. PointFire Power Translator, which both support a lot of languages, but has beenĮdited to be less about those products and more about Microsoft language technology. Written in the context of specific SharePoint products, PointFire 365 and Language support has also grown in recent years, with a few more languages The quality that you get from Microsoft AzureĬognitive Services is much higher than what you get from the free translation Machine translation now has quality that sometimes rivals human beings. Has come a long way in the past few years.įrom barely intelligible gibberish in some languages a few years back, ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |