Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

...

Info

Types of engines

  • Custom

    • Domain-adapted, AI-boosted

    • Stock+

  • Stock

Custom engines

...

Info

AI-Boosted engines

The option to train AI-boosted engines is available from Globalese V5. These engines are combining the terminology and style accuracy of a domain-adapted engine with the linguistic capabilities of large language models. In Globalese V5, AI-Boosted Engines use currently GPT models from OpenAI. The AI-boosting option is currently available for domain-adapted engines. AI-boosted engines typically provide the best results in most cases. They are especially effective if the engine is not designed exclusively for a very specific domain, such as the translation of a technical documentation. However, the results may vary, as GPT models from OpenAI are non-deterministic by default., especially as it is supporting dynamic keyword lists.

Please note that GPT models from OpenAI MS Azure are currently available as a beta service. AI-boosted engines can only be used in the Cloud Text translation scenario.

...

The following table shows the minimum and recommended number of segments.

Includes stock corpora?

Minimum volume (segments)

Recommended volume (segments)

Yes

15,000 master

100,000+ master

No

15,000 master
200,000 total

100,000+ master
1,000,000+ total

Typical training time

The typical training time for domain-adapted engines is between 10 and 28 hours.

...