Yandex introduced a new version of the technology for translating text in photos and images using neural networks: the company used a large language model to translate images taking into account the context. This was reported to RB.RU by the company’s press service.
Author:
https://rb.ru/author/ntihonov/
Subscribe to RB.RU on Telegram
The update is available in the translator and the browser, and will then appear in the Smart Camera. The YandexGPT model recognizes the style of the original text and avoids puns, for example, in advertising slogans or newspaper headlines. The new technology reportedly selects more precise words in phrases with multiple meanings and does not translate expressions word for word. The larger language model works for images with English text.
“Thanks to this, the quality of translation of simple texts, such as the composition of cosmetic products, and complex ones, such as journalistic articles, encyclopedias and instructions, has increased,” the company said.
Yandex recommends using a translator both on a tourist trip to study a restaurant menu and at work to read the nuances of technical documentation in a foreign language. To make text on images easier to read, Yandex has improved its display in several dozen languages, the company reported.
In early October, Yandex launched the Neuro in Search service, which analyzes and combines information from multiple sources into a single response. Before this, Yandex Browser also added a text editor running on the YandexGPT neural network, a neural translator, and a tool for briefly retelling texts.
Author:
Nikolai Tikhonov
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.
