Pre-translate a document

In this guide: Starting the translation process for a new document can be overwhelming as you realize there is so much work to do. Learn how to pre-translate your documents on Redokun using previously approved translations or machine translation in order to reduce your team's workload.

Overview

Pre-Translate is a powerful feature in Redokun that helps automate the translation process by leveraging your previously approved translations (Translation Memory) and AI-powered Machine Translation (MT). This reduces manual work and speeds up translation while maintaining accuracy and consistency.

Go from this:

to this:

in seconds...

How to Use Pre-Translate

You can launch Pre-Translate from two places:

From the Document Detail Page to apply pre-translation to all selected languages.
From the Web Editor to pre-translate only a specific language.

Step 1: Open the Pre-Translate Window

Navigate to your document's detail page or open the Web Editor for a specific language. The screenshots below illustrate both options:

Pre-Translate from the Document Detail Page: This option allows you to apply pre-translation to all selected languages at once.

Pre-Translate from the Web Editor: This allows you to pre-translate only a specific language within an open document.

Click the Pre-Translate button.

Step 2: Choose Pre-Approved Translations

Redokun first applies Pre-Approved Translations using your Translation Memory. If a segment has been previously translated and stored, it will be reused.

Mark all as “Confirmed” – Uses exact word-for-word matches, regardless of surrounding context. This option is selected by default.
Mark as “Draft” for non-context aware translations – Uses exact matches, but if the surrounding context is different, the segment is marked as Draft for review.

Step 3: Enable AI Machine Translation (Optional, available on certain plans – see pricing)

If a segment is not found in the Translation Memory, Redokun can use Machine Translation to complete it.

Toggle AI Machine Translation ON/OFF.
Select your preferred translation provider for each language:
- DeepL (if available for the language pair)
- Google Translate (if available for the language pair)

You can check the availability of the Pre-translate with Machine Translation from the Pricing page.

Step 4: Launch Pre-Translation

Click Launch Pre-Translation to apply the selected settings. The document (or selected language) will be automatically pre-translated in seconds.

Summary

Pre-Translate applies Translation Memory and AI-powered Machine Translation to reduce manual work.
You can choose to mark TM matches as Confirmed (ignoring context) or Draft (if the surrounding context differs).
Machine Translation supports DeepL and Google Translate (if available for the language pair and supported by the user's plan).
Pre-Translate can be launched for all languages or a single language from the Web Editor.

This updated Pre-Translate feature gives you more control over how translations are applied, ensuring both efficiency and accuracy in your workflow.

Technical Concepts & Terminology Clarifications

What is Context?

The term "context" simply refers to the text surrounding a particular text segment.

What is a 100% Match?

100% matches occur when a source segment you're currently translating is identical to another source segment your team has translated before.

In these cases, you can usually reuse the same translation with a good amount of confidence.

What is a 100% Match with Same Context?

This is same as the above but it takes the matching algorithm a step further.

A 100% Match with Same Context occurs when both of the following conditions are met:

A source segment you're currently translating is identical to another source segment your team has translated before.
The source segment in both the new document and the old document share the same surrounding segments (context).

This matching algorithm is especially useful if you regularly translate documents with repetitive sections. Brochures and product catalogs are a good example as they are likely to have a few parts that do not change as your team cycles through different editions. For instance, the company profile or the descriptions for a product line. With a deeper level matching algorithm, you can safely reuse your translations for the parts that are repeated across different documents. And they likely won’t require any editing at all.

Compared to a 100% Match, translations marked as 100% Match with Same Context have an even higher likelihood of being accurate and on-topic.

The following visual highlights which segments are considered in determining whether there is a 100% Match or 100% Match with Same Context.