diff --git a/docs/Draft-Generation/understanding-drafts.md b/docs/Draft-Generation/understanding-drafts.md index 77a2ea5..f3394f3 100644 --- a/docs/Draft-Generation/understanding-drafts.md +++ b/docs/Draft-Generation/understanding-drafts.md @@ -25,7 +25,13 @@ The system learns by seeing the same sentence written in multiple languages, one The most important point to remember is that these sentences need to say the same thing in both languages. This is the same principle that allowed scholars to learn hieroglyphics from the Rosetta Stone: the same text was written in three different languages, allowing comparison between a language that was already understood and one that was not. -Text that is available in both the language you are translating from, and the language you are translating to, is known as “parallel text”. In general, the more parallel text you have, the better the system will learn the language. For most projects, this parallel text will be your reference text, and the translation work you have already completed. At this time, we recommend that you have at least the New Testament translated. +Text that is available in both the language you are translating from, and the language you are translating to, is known as “parallel text”. For most projects, this parallel text will be your reference text, and the translation work you have already completed. In general, the more parallel text you have, the better the system will learn the language. If you plan to use draft generation with fewer than 6000 completed verses, please review the [Guidelines for New Testament Draft Generation](https://help.scriptureforge.org/new-testament-drafting). + +:::tip + +Because it works at the sentence level, the translation model limits the length of sentences to be drafted. This length is different for different languages because the model handles the words differently. Single Bible verses will not be affected, and most short verse ranges are safe to use. However, long ranges in the source text combining multiple verses may be cut short and not drafted in full. Long passages like book introductions may also be affected. + +::: ## Example use cases {#937c1db4b24d4e85bfc2acc489bf456b} diff --git a/docs/faq.md b/docs/faq.md index c421182..26c28a8 100644 --- a/docs/faq.md +++ b/docs/faq.md @@ -73,3 +73,6 @@ slug: /faq _When you make changes to your draft, Scripture Forge saves a version of those changes that you may access via the history tab. You may revert your project to an older version from here by clicking the "Restore this version" button._ +6. Why is my book introduction cut short? + + _Scripture Forge uses the NLLB model to generate drafts. NLLB is a sentence model, and it is most accurate with short segments of text. To maximize accuracy, there is a limit of 200 tokens (word parts) per translated segment, and any text after that point is cut off. Scripture verses are translated one-by-one and very rarely exceed this limit. Paragraph-length book introductions that are longer than the allowed length will be cut off short, and only the first portion will be translated._