---
name: watson-knowledge-studio-language-support
title: Language support
description: Support for multiple languages does not mean that the product itself is translated. The Knowledge Studio user interfaces, messages, and documentation are available in English only.
last-updated: 2020-08-04
---

> ## Documentation Index
> The table of contents for this documentation set is at https://cloud.ibm.com/docs/watson-knowledge-studio?format=markdown
> The index for all IBM Cloud docs is at: https://cloud.ibm.com/docs/llms.txt
> Use these files to discover more information as needed.

{:shortdesc: .shortdesc}
{:external: target="_blank" .external}
{:deprecated: .deprecated}
{:important: .important}
{:note: .note}
{:tip: .tip}
{:preview: .preview}
{:beta: .beta}
{:pre: .pre}
{:codeblock: .codeblock}
{:screen: .screen}

This documentation is for IBM Watson® Knowledge Studio on IBM Cloud®. To see the documentation for the previous version of Knowledge Studio on IBM Marketplace, [click this link](https://cloud.ibm.com/docs/knowledge-studio?topic=knowledge-studio-language-support&format=markdown).
{: tip}

# Language support
{: #language-support}

IBM Watson® Knowledge Studio provides support for training a model in several languages.

Support for multiple languages does not mean that the product itself is translated. The Knowledge Studio user interfaces, messages, and documentation are available in English only.
{: shortdesc}

You can train a model in the following languages:

- English (the default language)
- Arabic
- Brazilian Portuguese
- Chinese (Simplified)
- Chinese (Traditional)
- Dutch
- French
- German
- Italian
- Japanese
- Korean
- Spanish

Support includes the ability to add documents in these languages to a workspace, add dictionaries, run pre-annotation, use the ground truth editor to annotate documents, and train a machine learning model. When you select a language, the system applies language-specific templates to handle dictionary entries, text tokenization, and sentence segmentation. For information about how the system handles dictionaries in different languages, see [Dictionaries](https://cloud.ibm.com/docs/watson-knowledge-studio?topic=watson-knowledge-studio-dictionaries&format=markdown#wks_dictionaries).

The rule editor and rule-based model cannot handle bidirectional text, so cannot be used with Arabic documents.
{: important}

## Restrictions
{: #lang-restrictions}

Because of character restrictions in the underlying machine learning technology, entries in the type system cannot contain spaces and can include only the following ASCII characters:

- A through Z and a through z
- 0 through 9
- The underscore character: _

The following rules also apply:

- The first character in the name must be alphabetical.
- The entity type name length cannot exceed 64 characters.
- The relation type name length cannot exceed 128 characters.

Thus, for example, when a human annotator annotates Japanese text in the ground truth editor, the entity type and relation type names that can be applied will not be in Japanese.

### Related tasks

[Configuring support for Arabic](https://cloud.ibm.com/docs/watson-knowledge-studio?topic=watson-knowledge-studio-wks_langsupp_ar&format=markdown)