> For the complete documentation index, see [llms.txt](https://docs.datasaur.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.datasaur.ai/advanced/extensions/ml-assisted-labeling.md).

# ML-Assisted Labeling

## Overview

**ML-assisted labeling** helps automate data labeling for NLP projects. It supports open-source models, large language models (LLMs), and custom models for both span-based and row-based labeling tasks.

The extension generates labels automatically, helping reduce manual effort and allowing users to focus on reviewing results.

## Use cases

### Sentiment analysis

Use **ML-assisted labeling** to classify sentiment in reviews or other text data.

1. Create a row labeling project.
2. Click the gear icon from the extension panel on the right to open the **Manage extensions** dialog, and enable the **ML-assisted labeling** extension.

   <figure><img src="/files/9KrQiRV1too1I67Qilqd" alt=""><figcaption></figcaption></figure>
3. Select [**Sentiment Analysis**](/assisted-labeling/ml-assisted-labeling/sentiment-analysis.md) as the service provider.

   <figure><img src="/files/rR4ygzFLEGDbAeZ6ydaE" alt=""><figcaption></figcaption></figure>
4. Configure **Target text** and **Target question**.
5. Click **Predict labels**.
6. Review the predicted labels and click **Accept** or **Reject**.

   <figure><img src="/files/8fcm2xSYaIluIUDmGB2v" alt=""><figcaption></figcaption></figure>

### Span labeling with spaCy

Use the spaCy provider to automatically label entities in text.

1. Create a span labeling project.

   <figure><img src="/files/rQFFRQgriIzpQH2jQErC" alt=""><figcaption></figcaption></figure>
2. Click the gear icon from the extension panel on the right to open the **Manage extensions** dialog, and enable the **ML-assisted labeling** extension.

   <figure><img src="/files/9KrQiRV1too1I67Qilqd" alt=""><figcaption></figcaption></figure>
3. Select [**spaCy**](/assisted-labeling/ml-assisted-labeling/spacy.md) as the service provider.

   <figure><img src="/files/sML60IzBG0yL64WuhaZ1" alt=""><figcaption></figcaption></figure>
4. Click **Predict labels**.
5. Review the predicted labels and click **Accept** or **Reject**.

   <figure><img src="/files/sULJ0bE8R9pnbeqBNQLr" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}
For more information about other providers, see [Assisted Labeling - ML-Assisted Labeling](/assisted-labeling/ml-assisted-labeling.md).
{% endhint %}