Rome – October 25, 2023
Translated today announced a new model of ModernMT, its adaptive machine translation (MT) system. The new model, called Hyper Adaptive, enables companies to translate billions of words at ultra-fast speeds without compromising quality. It is domain-specific and designed for use cases such as translating user-generated content, datasets for multilingual large language models, and web content for data mining activities.
In recent years, companies have approached Translated with requests to leverage the accuracy of ModernMT's adaptive MT system to quickly translate specialized, unique content and high volumes of ongoing content. While a generic adaptive MT model can handle the request, it is not designed to translate millions of words per minute in a specific domain.
Hyper Adaptive solves this issue by using sophisticated compression techniques and training the MT model for specific use cases based on the customer's previous translations and translation memories (TMs).The resulting MT model is much smaller than a generic adaptive model and can process content at ultra-fast speeds, in as little as 50ms for a typical sentence. Combined with Translated's dedicated data centers, it can translate the entire English Wikipedia (4.4 billion words) into another language in less than a day (3 million words per minute). By training directly using customer data, the Hyper Adaptive model achieves translation accuracy equal to or better than state-of-the-art custom adaptive MT models.
This solution helps companies maintain quality even when translating massive volumes of content at ultra-high speeds.
In some specific cases, such as user-generated content, combining the MT model with professional translators can further improve the quality of the output over time. Because the model is still adaptive, it can continue to improve after initial training through corrections and new TMs delivered to match the company's style.