Assisted Knowledge Graph Authoring: Human-Supervised Knowledge Graph Construction from Natural Language

Marcel Gohsen, Benno Stein
1/15/2024
cs.CL

No official code found. Best implementation: webis-de/waka (9 stars, MIT, last commit 2024-09-05).

Abstract

Encyclopedic knowledge graphs, such as Wikidata, host an extensive repository of millions of knowledge statements. However, domain-specific knowledge from fields such as history, physics, or medicine is significantly underrepresented in those graphs. Although few domain-specific knowledge graphs exist (e.g., Pubmed for medicine), developing specialized retrieval applications for many domains still requires constructing knowledge graphs from scratch. To facilitate knowledge graph construction, we introduce WAKA: a Web application that allows domain experts to create knowledge graphs through the medium with which they are most familiar: natural language.

View on arXivView PDF

Code Implementations(1)

webis-de/wakaCommunity100%
MIT

Construct and author knowledge graphs from text.

90CSS, HTMLNov 2, 20232 years agoMIT

Similar Papers

Construction of Knowledge Graphs: State and Challenges

83% match2023

Automated Construction of a Knowledge Graph of Nuclear Fusion Energy for Effective Elicitation and Retrieval of Information

82% match2025

WikiCoder: Learning to Write Knowledge-Powered Code

82% match1 repo222023

Wikontic: Constructing Wikidata-Aligned, Ontology-Aware Knowledge Graphs with Large Language Models

82% match2025

Knowledge Graphs: The Future of Data Integration and Insightful Discovery

81% match2024

NASA Science Mission Directorate Knowledge Graph Discovery

81% match2023

Cite this paper

@article{gohsen2024assisted,
  title  = {Assisted Knowledge Graph Authoring: Human-Supervised Knowledge Graph Construction from Natural Language},
  author = {Marcel Gohsen and Benno Stein},
  year   = {2024},
  eprint = {2401.07683},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2401.07683v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2401.07683.svg)](https://codeofpaper.com/paper/2401.07683)

Discussion