Business Document Information Extraction: Towards Practical Benchmarks
This work addresses the problem of automating B2B document communication for businesses, but it is incremental as it primarily reviews and redefines existing problems without introducing new methods or data.
The paper identifies that existing benchmarks for document information extraction (IE) do not align with practical business needs, and it defines new problems (KILE and LIR) to address this gap, though it does not provide experimental results or concrete numbers.
Information extraction from semi-structured documents is crucial for frictionless business-to-business (B2B) communication. While machine learning problems related to Document Information Extraction (IE) have been studied for decades, many common problem definitions and benchmarks do not reflect domain-specific aspects and practical needs for automating B2B document communication. We review the landscape of Document IE problems, datasets and benchmarks. We highlight the practical aspects missing in the common definitions and define the Key Information Localization and Extraction (KILE) and Line Item Recognition (LIR) problems. There is a lack of relevant datasets and benchmarks for Document IE on semi-structured business documents as their content is typically legally protected or sensitive. We discuss potential sources of available documents including synthetic data.