Translated Levels Up Adaptive MT with Expanded Document Context

The company's machine translation (MT) system now leverages up to 100,000 words of document content to provide translation suggestions, drastically reducing the time to edit MT suggestions (TTE). The upgrade is available at no additional cost to translators and clients.

Rome – Jul 12, 2023

Translated, a leading provider of AI-powered language solutions, today announced a significant expansion to its document-level adaptation, a standout feature of ModernMT, the company’s award-winning adaptive machine translation (MT) system. ModernMT can now leverage up to 100,000 words of document content, 4 times more than the best large language models, to preserve style and terminology preferences, providing unparalleled document-specific accuracy in MT suggestions and significantly reducing the time to edit MT suggestions (TTE).

Expanded document-level adaptation enhances the translation of complex, detailed, or regulatory content, such as annual reports, legal documents, marketing materials, and technical documentation. The upgrade is available immediately at no additional cost to all ModernMT customers, users of Translated's CAT tool Matecat who have an active ModernMT subscription, and translators working on projects for Translated's clients.

Patent-awarded adaptive machine translation


ModernMT took inspiration from the human brain not just for its neural structure but for its incredible capacity to adapt, learn from new experiences, and interact with other humans. The result is a unique, patent-awarded, human-in-the-loop approach, a symbiosis where machines and humans continuously assist each other, providing outstanding translation quality and process efficiency that surpasses any previous method.

Addressing Gender Bias and Inconsistent Terminology

Document-level adaptation in machine translation, pioneered by ModernMT in 2017, initially involved referencing similar sentences in translation memories and some translated segments. Despite the pioneering nature of this approach, early implementations faced challenges: translators struggled with issues such as gender bias and inconsistent terminology due to the distance between the segment they were working on and its related context. By taking into account all edits in the document, even those in completely different or distant segments, the MT model is now able to provide document-specific translation suggestions. This development significantly reduces the need for repeated corrections of elements such as pronouns.

Since the very beginning, Translated has been committed to combining the sensitivity of translators with the speed of machines. With the introduction of expanded document-level adaptation, translators can now translate more words per hour and deliver higher overall quality, which leads to increased earnings. As a result, Translated's customers now enjoy more accurate translations delivered in record time.
Marco Trombetti – Translated CEO

Available in Matecat and Other Major CAT Tools

Expanded document-level adaptation is now available in ModernMT. It is also integrated into directly supported CAT tools (Matecat, Trados, and memoQ) via ModernMT's API. Translated's clients will indirectly benefit from this upgrade, as the company's translation services are fully based on Matecat.

For all translators, Matecat is available for unlimited use free of charge at matecat.com, while ModernMT is offering a free one-month trial at modernmt.com.

Get the Most
Advanced CAT Tool

Just drop a file and start translating it with Matecat.

Try Matecat Now