Text mining and knowledge graph construction from geoscience literature legacy: A review

Abstract

In the recent decade, knowledge graph has been a key technique under quick development in artificial intelligence. Due to its great potential for tackling big data and solving complex scientific questions in the geosciences, it has attracted the attention of both computer scientists and geoscientists. In this paper, we review concepts and technologies relevant to the knowledge graph, the workflow of geoscience knowledge graph construction, and state-of-the-art examples from several geoscience disciplines. There are two general strategies for constructing geoscience knowledge graphs: top-down and bottom-up. The detailed technologies include geoscience domain knowledge modeling, data collection, knowledge extraction, knowledge cleaning and fusion, knowledge storage, and knowledge service and discovery. A few recent studies have shown that knowledge graph is a useful tool for improving our understanding of the evolution of the Earth and can assist in data-intensive geoscience studies. At the end of the paper, we discuss the best practices from the studies reviewed and propose research topics for future work. Both knowledge and rules in existing human-curated databases and text mining from the literature should be leveraged in constructing geoscience knowledge graphs. Moreover, development of a higher level schema for existing ontology models and a comparable training corpus should be considered.