View the PDF Days Europe 2025 agenda
This presentaton is part of PDF Days Europe 2025.
Register now!
View our terms and conditions.
Understanding the structure of PDF tables and extracting data from them
Fully explainable vs generative AI algorithms
Excerpt: Recent advances in generative AI have captured the headlines in recent years and its advantages and limitations are well known among a wide audience. But the more traditional form of AI, the expert system, which enables a fully explainable algorithm and predictable outcome for a given data source, has also quietly been making progress lately. This presentation will introduce how both approaches can be used to understand the structure of tables in PDF documents, their respective advantages and di … Read moreAbout the presenter(s)
Tamir Hassan has over a decade of experience in the area of document engineering. After writing his doctoral thesis on the topic User-Guided Information Extraction from Print-Oriented Documents, he worked … Read more
Description
Recent advances in generative AI have captured the headlines in recent years and its advantages and limitations are well known among a wide audience. But the more traditional form of AI, the expert system, which enables a fully explainable algorithm and predictable outcome for a given data source, has also quietly been making progress lately.
This presentation will introduce how both approaches can be used to understand the structure of tables in PDF documents, their respective advantages and disadvantages, and will give examples of how these approaches can be used for automated data extraction.