Business Document Information Extraction: Towards Practical Benchmarks

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.

Automated summary

This paper explores the problem of information extraction from semi-structured documents, highlighting the practical needs missing in common definitions and proposing the Key Information Localization and Extraction (KILE) and Line Item Recognition (LIR) problems. Due to the legal protection of content in semi-structured business documents, there is a lack of relevant datasets and benchmarks.