Knowledge Triplets Derivation from Scientific Publications via Dual-Graph Resonance

Kai Zhang, Xiaozhong Liu

Abstract: Scientific Information Extraction (SciIE) is a vital task and is increasingly being adopted in domain-specific (e.g., Biomedical) data mining to conceptualize and epitomize knowledge triplets from scientific literature. Existing relation extraction methods aim to extract explicit triplet knowledge from documents, however, they can hardly perceive unobserved factual relations. Recent generative methods have more flexibility, but their generated relations will encounter trustworthiness problems. In this paper, we propose a novel \textbf{E}xtraction-\textbf{C}ontextualization-\textbf{D}erivation (\textbf{ECD}) strategy to generate a document-specific and entity-expanded dynamic graph from a shared static knowledge graph. Then, we propose a novel \textbf{D}ual-\textbf{G}raph \textbf{R}esonance \textbf{N}etwork (\textbf{DGRN}) which can generate richer explicit and implicit relations under the guidance of static and dynamic knowledge topologies. Experiments conducted on a public PubMed corpus validate the superiority of our method against several state-of-the-art baselines.