Unsupervised Knowledge Graph Construction and Event-centric Knowledge Infusion for Scientific NLI
This addresses the lack of domain-specific knowledge in pre-trained models for scientific NLI, though it appears incremental as it builds on existing knowledge graph and infusion approaches.
The paper tackles the problem of natural language inference for scientific texts by constructing a scientific knowledge graph without labeled data and integrating it into pre-trained models through event-centric knowledge infusion, achieving state-of-the-art performance.
With the advance of natural language inference (NLI), a rising demand for NLI is to handle scientific texts. Existing methods depend on pre-trained models (PTM) which lack domain-specific knowledge. To tackle this drawback, we introduce a scientific knowledge graph to generalize PTM to scientific domain. However, existing knowledge graph construction approaches suffer from some drawbacks, i.e., expensive labeled data, failure to apply in other domains, long inference time and difficulty extending to large corpora. Therefore, we propose an unsupervised knowledge graph construction method to build a scientific knowledge graph (SKG) without any labeled data. Moreover, to alleviate noise effect from SKG and complement knowledge in sentences better, we propose an event-centric knowledge infusion method to integrate external knowledge into each event that is a fine-grained semantic unit in sentences. Experimental results show that our method achieves state-of-the-art performance and the effectiveness and reliability of SKG.