This article outlines several Data Source guidelines for making the most of LILT's technology.
To ensure the highest quality model adaptation, translation memory files should mostly consist of full natural-language sentences. Uploading a large quantity of short segments may degrade model performance and require a model reset.
The maximum file size for TM uploads is 200 MB. For file sizes larger than 200 MB, the files can be zipped before upload.
For self-managed customers, processing of TMs larger than 3,000 parallel segments is only recommended when a GPU is installed on the system. Otherwise, memory updates may be slow.
LILT processes TMs much faster when using a GPU. The exact rate varies by language pair, type of GPU, and amount of CPU and RAM available to the system.