---
name: natural-language-understanding-customizing
title: Overview - Customizing models
description: You can extend Natural Language Understanding with custom models for supported feature and language combinations.
last-updated: 2022-08-02
---

> ## Documentation Index
> The table of contents for this documentation set is at https://cloud.ibm.com/docs/natural-language-understanding?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}
{:tip: .tip}
{:note: .note}
{:beta: .beta}
{:pre: .pre}
{:important: .important}
{:codeblock: .codeblock}
{:screen: .screen}
{:javascript: .ph data-hd-programlang='javascript'}
{:java: .ph data-hd-programlang='java'}
{:python: .ph data-hd-programlang='python'}
{:swift: .ph data-hd-programlang='swift'}

# Overview - Customizing models
{: #customizing}

You can extend Natural Language Understanding with custom models for supported feature and language combinations.
{: shortdesc}

## Before you begin
{: #customizing-before-you-begin}

1. If you haven't done so already, [get started](https://cloud.ibm.com/docs/natural-language-understanding?topic=natural-language-understanding-getting-started&format=markdown) with Natural Language Understanding.
1. Check [Language support for custom models](#language-support-for-custom-models) to make sure that the custom model you want to create is supported.
1. Follow the customization instructions for one of the following features.
   - [Entities and relations](https://cloud.ibm.com/docs/natural-language-understanding?topic=natural-language-understanding-entities-and-relations&format=markdown)
   - [Categories (Beta)](https://cloud.ibm.com/docs/natural-language-understanding?topic=natural-language-understanding-categories&format=markdown)
   - [Classifications](https://cloud.ibm.com/docs/natural-language-understanding?topic=natural-language-understanding-classifications&format=markdown)

## Language support for custom models
{: #language-support-for-custom-models}

Check the *Custom model support* columns in the tables on the [Language support](https://cloud.ibm.com/docs/natural-language-understanding?topic=natural-language-understanding-language-support&format=markdown) page to see the features that support custom models for each language.

## Specifying training parameters for custom models
{: #training-for-custom-models}

As part of the request to create or update a custom model, you may optionally include a training parameters object that specifies attributes of the model. For details, see feature-specific [Classifications training parameters](https://cloud.ibm.com/docs/natural-language-understanding?topic=natural-language-understanding-classifications&format=markdown#classification-training-parameters).

## Targeted sentiment for custom model entities
{: #targeted-sentiment-for-custom-entities}

For English only, you can get sentiment scores for each custom model entity that is detected by the service by setting the `sentiment: true` option in the entities object. No other languages support targeted sentiment for custom model entities.

## Usage restrictions for custom models
{: #usage-restrictions-for-custom-models}

The maximum number of models that can be trained via the Natural Language Understanding customization API in parallel is 3.