Advantages, disadvantages, and best practices

Live Webinar: Data extraction from documents: template-based or AI-based

In companies today, numerous documents are in circulation. Yet the data inside needs to be captured so it can be used for further processing. Just think about how the Finance team needs access to data in invoices. Or how the market analytics department needs access to utility bill data to perform market research. Brokers who need to retrieve data from purchase orders, IT departments that require data extraction as a part of a paperless workflow. The list goes on.

To avoid the manual work to retrieve the data from structured and unstructured documents, various solutions exist to automate the process: either through template-based data extraction or using AI-based data extraction. However, what are the current advantages and disadvantages of each approach?

During this webinar, you will learn more about:

  • Structured, semi-structured and unstructured documents
  • When to use template-based, or AI-based data extraction
  • Some real-life use cases

live webinar iText pdf2Data

Pavel Chermyanin

Pavel Chermyanin is the product manager for iText pdf2Data. He has a strong development background as well as experience in product management. He joined to iText in 2019. He believes that the table-based approach is still relevant. 


Pavel Chermyanin

Product Manager

André Lemos

André Lemos is the VP of Products at iText, a leading technology company active in the digital documents space. iText's flagship product is iText 7, an open source library to create and manipulate PDF documents in Java and .NET (C#).

André has a strong development background, and has been involved in product management for 9 years in areas ranging from health, physiotherapy and biosignals research. In his free-time you will find him cruising around the city on his bike.


André Lemos

VP of Products