A Web-scale system for scientific knowledge exploration
This enables efficient exploration of scientific knowledge for researchers and practitioners, though it appears incremental as it builds on existing methods for concept identification and tagging.
The paper tackles the problem of organizing Web-scale scientific knowledge by developing a system that identifies hundreds of thousands of concepts, tags them to hundreds of millions of publications, and builds a six-level hierarchy, resulting in the most comprehensive cross-domain scientific concept ontology with over 200,000 concepts and 1 million relationships.
To enable efficient exploration of Web-scale scientific knowledge, it is necessary to organize scientific publications into a hierarchical concept structure. In this work, we present a large-scale system to (1) identify hundreds of thousands of scientific concepts, (2) tag these identified concepts to hundreds of millions of scientific publications by leveraging both text and graph structure, and (3) build a six-level concept hierarchy with a subsumption-based model. The system builds the most comprehensive cross-domain scientific concept ontology published to date, with more than 200 thousand concepts and over one million relationships.