# Configure NER models

NER stands for **Named Entity Recognition**. It detects named entities in text.

Supported entity types:

* Person
* Location
* Organization

Detected entities are not underlined by the spelling engine.

NER uses language-specific model files stored in the AppServer resources directory.

The default location is `<WebSpellChecker_installation_path>/AppServer/Resources/`. The actual path is controlled by `ResourcesDir` in `AppServerX.xml`. See [AppServer parameters](/v6.12.0/deployment/configuration/application-server/appserver-parameters.md).

NER is configured via the `NERModel` tag in `AppServerX.xml`. It is nested under the Hunspell spell engine options for a CheckKit.

{% hint style="info" %}
Each NER model is roughly **\~330 MB on disk**. When loaded, it uses roughly **\~330 MB of RAM**.
{% endhint %}

### Warning: failed to load NER model

If the model file was not downloaded during installation, AppServer logs warnings. Example:

```
04/03/26:16:28:11.843   #15520:0    Subsystem_General   Error Failed to load NER model: 'en/ner_model_en.dat'.
```

{% hint style="warning" %}
This warning usually means the model file is missing in the AppServer resources directory. It often happens when the download step was skipped during installation.

If your server has no Internet access, see [Manually downloading resources (offline installation)](/v6.12.0/deployment/installation/manually-downloading-resources-offline-installation.md).
{% endhint %}

### Default NER enablement by language

<table data-header-hidden><thead><tr><th width="187">Language</th><th>Supported language IDs</th><th>Model file</th><th>Default status</th></tr></thead><tbody><tr><td><strong>Language</strong></td><td><strong>Supported language IDs</strong></td><td><strong>Model file</strong></td><td><strong>Default status</strong></td></tr><tr><td>English</td><td><ul><li>en_US</li><li>en_GB</li><li>en_CA</li><li>en_AU</li><li>en_NZ</li><li>en_ZA</li></ul></td><td><code>en/ner_model_en.dat</code></td><td>Enabled</td></tr><tr><td>German</td><td><ul><li>de_DE</li><li>de_AT</li><li>de_CH</li></ul></td><td><code>de/ner_model_de.dat</code></td><td>Disabled</td></tr><tr><td>Spanish</td><td><ul><li>es_AR</li><li>es_CL</li><li>es_CO</li><li>es_CR</li><li>es_DO</li><li>es_ES</li><li>es_MX</li><li>es_PE</li><li>es_PR</li><li>es_UY</li><li>es_VE</li></ul></td><td><code>es/ner_model_es.dat</code></td><td>Disabled</td></tr></tbody></table>

### Change NER settings (enable/disable)

1. Open `<WebSpellChecker_installation_path>/AppServer/AppServerX.xml`.
2. Find the `NERModel` tag for the language you need.
3. Change the `Enabled` attribute:
   * Set `Enabled="true"` to enable NER (common for German/Spanish).
   * Set `Enabled="false"` to disable NER (optional for English).

Example:

```xml
<NERModel Enabled="true" Path="de/ner_model_de.dat" ProbabilityThreshold="0.5"/>
```

4. Save the file.

Restart AppServer to apply changes in `AppServerX.xml`.

To restart: [stop](https://docs.wproofreader.com/v6.12.0/deployment/configuration/spell-check-engine/pages/IA2KNQLXDh85TwDivL4y#mainappservercommands-stopappserverwindowslinux2.stopappserver) the application, then [start](https://docs.wproofreader.com/v6.12.0/deployment/configuration/spell-check-engine/pages/IA2KNQLXDh85TwDivL4y#mainappservercommands-startappserverwindowslinux1.startappserver) it again.

Use [Main AppServer commands](/v6.12.0/deployment/configuration/application-server/main-appserver-commands.md).

{% hint style="warning" %}
If you enable NER but the model file is missing, you will still see the “Failed to load NER model” warning in logs.
{% endhint %}


---

# Agent Instructions: Querying This Documentation

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

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.wproofreader.com/v6.12.0/deployment/configuration/spell-check-engine/configure-ner-models.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.