Docs2KG: Unified Knowledge Graph Construction from Heterogeneous Documents Assisted by Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Qiang, Luo, Yuanyi, Zhang, Wenxiao, Li, Sirui, Li, Jichunyang, Niu, Kai, Kong, Xiangrui, Liu, Wei
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929374743232512
author Sun, Qiang
Luo, Yuanyi
Zhang, Wenxiao
Li, Sirui
Li, Jichunyang
Niu, Kai
Kong, Xiangrui
Liu, Wei
author_facet Sun, Qiang
Luo, Yuanyi
Zhang, Wenxiao
Li, Sirui
Li, Jichunyang
Niu, Kai
Kong, Xiangrui
Liu, Wei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_02962
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Docs2KG: Unified Knowledge Graph Construction from Heterogeneous Documents Assisted by Large Language Models
Sun, Qiang
Luo, Yuanyi
Zhang, Wenxiao
Li, Sirui
Li, Jichunyang
Niu, Kai
Kong, Xiangrui
Liu, Wei
Computation and Language
Artificial Intelligence
Information Retrieval
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.
title Docs2KG: Unified Knowledge Graph Construction from Heterogeneous Documents Assisted by Large Language Models
topic Computation and Language
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2406.02962