Lilt uses Machine Translation (MT) to provide quick translations and to provide translation suggestions to linguists working in Lilt Translate. Each Lilt Memory has its own MT model that can be managed from inside the Lilt Memory. Each MT model starts out as a copy of Lilt's baseline MT, built using training data. If the
Adaptive memory option is enabled for the Lilt Memory, the MT adapts as linguists process translations in Lilt Translate.
Where MT is used in Lilt
- Lilt Translate MT segment suggestions.
- Pretranslation: Pretranslation comes with the option to utilize MT to translate any segments that don't have exact matches (100% or 101%).
- Instant translate documents and instant translate text: Self-managed customers can utilize MT to quickly translate documents and blocks of text.
MT segment suggestions
When working in Lilt Translate, translation suggestions are provided to linguists for the active segment. If there are any TM matches above 75%, the best match will be displayed as the suggestion. However, if there are no such TM matches, Lilt uses the associated MT to provide suggestions to the linguist. Note that if the language pair does not have MT support, no MT suggestions will be shown.