Yandex taught its YandexGPT (YaLM 2.0) language model for quick and concise retelling of text. The user only needs to upload a link to an Internet article to the neural network, and the model will compile a summary with the main theses. This was reported by the press service of the company.
Now the function is working in test mode on the 300.ya.ru service.
The neural network adapts to Russian texts up to 30 thousand characters. It will take less than a minute to process and select the main theses. In this case, the user can share a link to a summary in instant messaging.
However, the technology has limitations, it is not capable of analyzing any text.
“Neural networks cannot yet recount such items. Try another ”, the service issues such a message when you try to get summaries of a long post in one of the Russian media.
At the same time, it does not specify what features the text must have in order for the neural network to be able to analyze it.
The service, in addition to retelling, provides an API for developers, so they can get a link to a shortened version of the text without using the web interface. The API is also in beta so far: suggestions for its development can be sent to the feedback form.
YandexGPT (YaLM 2.0) was released on May 17. It is available to users in “Let’s Think” mode in Alice. The neural network was trained in two stages on Yandex supercomputers. The company has also incorporated it into its Masterroom app.
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.
