> For the complete documentation index, see [llms.txt](https://docs.tryprotege.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.tryprotege.com/review/content-scanning/translation-support.md).

# Translation Support

Protege Review supports multi-language document scanning and translation capabilities, enabling you to review and analyze content in languages other than English. This feature is particularly valuable for organizations operating across multiple regions or reviewing international marketing materials.

## Overview

The translation feature allows you to:

* Scan and analyze documents written in various languages
* Automatically translate content to English for policy review
* Apply policy checks to translated content
* Review original and translated versions side-by-side

## Supported Languages

Protege Review supports translation for major world languages, including but not limited to:

* Spanish
* French
* German
* Italian
* Portuguese
* Japanese
* Chinese (Simplified and Traditional)
* Korean
* Arabic
* And many more

For a complete list of supported languages, contact our support team.

## How Translation Works

1. **Document Detection**: When a document is scanned, Protege Review automatically detects the language
2. **Translation**: Non-English content is translated to English using advanced AI models
3. **Policy Application**: Policies and compliance checks are applied to the translated content
4. **Review**: Reviewers can view both the original and translated versions
5. **Feedback**: Policy feedback references both languages for context

## Using Translation in Scanner Jobs

### For Content Scanning Jobs

When creating or editing a content scanning job:

1. Navigate to **Content Scanner** in the dashboard
2. Create a new job or edit an existing one
3. In the job configuration, translation is automatically enabled for detected non-English content
4. Policy checks will be applied to the translated version
5. Results will show both original and translated content

### For Document Reviews

Translation is also available for individual document reviews:

1. Upload or scan a document in any supported language
2. Protege Review will detect the language and offer translation
3. Review the translated content with standard policy checks
4. Provide feedback referencing both original and translated text

## Translation Accuracy

* Translation uses state-of-the-art AI models for high accuracy
* Legal and marketing terminology is handled with specialized context
* Complex sentences and idioms are translated to preserve meaning
* For critical compliance work, human review of translations is recommended

## Best Practices

* **Review Original Content**: Always reference the original language version when making final compliance decisions
* **Cultural Context**: Be aware that some marketing claims or language may have different implications across cultures
* **Custom Terminology**: Contact support to add industry-specific terminology to improve translation accuracy
* **Disclosure Requirements**: Ensure translated disclosures maintain legal accuracy and completeness

## Enabling Translation

Translation support is automatically enabled for all scanner jobs and document reviews. No additional configuration is required.

For questions about translation capabilities or to request support for additional languages, contact <support@tryprotege.com>.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.tryprotege.com/review/content-scanning/translation-support.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
