Yandex has improved machine translation in its translator by retraining its neural network using texts from the YandexGPT language model. This was reported by the press service.
Subscribe to RB.RU on Telegram
Thanks to additional training, the service more accurately understands the context, better recognizes phraseological units and navigates professional vocabulary.
Now the Yandex translator also better understands connections within sentences and at the level of the entire text. Additionally, the service has become more accurate in recognizing meanings in texts on specific topics.
When creating training examples for the translator’s neural network, the company used a specialized model from the YandexGPT family. The developers adapted it for translation tasks.
Test results showed that with the updated technology, the service is more responsive to requests in 57% of cases.
Improved automatic translation is used in Yandex Translator, Search and in-browser video translation.
Author:
Natalia Gormaleva
Source: RB
I am a professional journalist and content creator with extensive experience writing for news websites. I currently work as an author at Gadget Onus, where I specialize in covering hot news topics. My written pieces have been published on some of the biggest media outlets around the world, including The Guardian and BBC News.
