Docs2KG: Unified Knowledge Graph Construction from Heterogeneous Documents Assisted by Large Language Models
This addresses the challenge of information seeking and insight formulation in enterprise data lakes where 80% of data is unstructured, offering a flexible solution for knowledge representation.
The paper tackles the problem of extracting information from heterogeneous unstructured documents (emails, web pages, PDFs, Excel files) in enterprise data lakes, introducing Docs2KG, a framework that dynamically constructs a unified knowledge graph for efficient querying and exploration, with the system being publicly accessible online.
Even for a conservative estimate, 80% of enterprise data reside in unstructured files, stored in data lakes that accommodate heterogeneous formats. Classical search engines can no longer meet information seeking needs, especially when the task is to browse and explore for insight formulation. In other words, there are no obvious search keywords to use. Knowledge graphs, due to their natural visual appeals that reduce the human cognitive load, become the winning candidate for heterogeneous data integration and knowledge representation. In this paper, we introduce Docs2KG, a novel framework designed to extract multimodal information from diverse and heterogeneous unstructured documents, including emails, web pages, PDF files, and Excel files. Dynamically generates a unified knowledge graph that represents the extracted key information, Docs2KG enables efficient querying and exploration of document data lakes. Unlike existing approaches that focus on domain-specific data sources or pre-designed schemas, Docs2KG offers a flexible and extensible solution that can adapt to various document structures and content types. The proposed framework unifies data processing supporting a multitude of downstream tasks with improved domain interpretability. Docs2KG is publicly accessible at https://docs2kg.ai4wa.com, and a demonstration video is available at https://docs2kg.ai4wa.com/Video.