---
metadata:
  - name: generator
    content: Diplodoc Platform v5.52.0
alternate:
  - https://catboost.ai/docs/en/concepts/python-text-processing.md
  - href: en/concepts/python-text-processing.md
    type: text/markdown
    title: Markdown version
  - href: ../llms.txt
    type: text/markdown
    title: llms.txt
---
> **Documentation Index:** Fetch the complete configuration index at https://catboost.ai/docs/en/llms.txt

# Text processing

Text Processing is used to solve different tasks, including but not limited to:
- Use text data by machine learning algorithms.

    Raw texts can not be handled by machine learning algorithms and therefore must be preprocessed.

- Improve the quality of resulting models.

    The usage of different types of text preprocessing (i.e., excluding numbers from the text or replacing upper case words with lower-case ones) can lead to significant improvements in the quality of the resulting model.


CatBoost provides the following classes for text processing:

- [Tokenizer](https://catboost.ai/docs/en/concepts/python-reference_tokenizer.md)
- [Dictionary](https://catboost.ai/docs/en/concepts/python-reference_dictionary.md)