What are the four extraction methods used in Document Understanding?

The four extraction methods used in Document Understanding include Regex Extractor, Form Extractor, Forms AI, and Semi-Structured AI.

Regex Extractor is employed to identify patterns in text data, allowing for the extraction of specific information based on regular expressions. This is particularly useful for structured data that fits predictable patterns, such as dates or identification numbers.

Form Extractor is designed to capture data from structured forms, where the layout is consistent. It leverages the structured nature of these documents to extract information accurately, making it a vital tool for automating data extraction processes.

Forms AI uses machine learning models to extract data from various types of forms. This method is adaptable and can handle more complex extraction tasks where the layout may vary, enhancing the extraction capabilities by training models on various documents.

Semi-Structured AI refers to methods that can handle semi-structured data, where the information does not follow a rigid format but still has a consistent structure. This approach is important as many real-world documents do not fit completely into structured or unstructured categories.

These methods support a wide range of document formats and structures, making them essential for effective document processing in automation scenarios.