KnowUREnvironment: Despite climate change being one of the greatest threats to humanity, many people are still in denial or lack motivation for appropriate action. A structured source of knowledge can help increase public awareness while also helping crucial natural language understanding tasks such as information retrieval, question answering, and recommendation systems. We introduce KnowUREnvironment — a knowledge graph for climate change and related environmental issues, extracted from the scientific literature. We automatically identify 210,230 domain-specific entities/concepts and encode how these concepts are interrelated with 411,860 RDF triples backed up with evidence from the literature, without using any supervision or human intervention. Human evaluation shows our extracted triples are syntactically and factually correct (81.69% syntactic correctness and 75.85% precision). The proposed framework can be easily extended to any domain that can benefit from such a knowledge graph.

For more details, please visit our Github repository

Publications:

  1. M. S. Islam, A. Proma, Y. Zhou, S. N. Akter, C. Wohn, E. Hoque, KnowUREnvironment: An Automated Knowledge Graph for Climate Change and Environmental Issues, The Role of AI in Responding to Climate Change, AAAI Fall Symposium Series, November 2022