Incorporating chains of reasoning over knowledge graph for distantly supervised biomedical knowledge acquisition

The increased demand for structured scientific knowledge has attracted considerable attention on extracting scientific relation from the ever growing scientific publications. Distant supervision is a widely applied approach to automatically generate large amounts of labelled sentences for scientific Relation Extraction (RE). However, the brevity of the labelled sentences would hinder the performance of distantly supervised RE (DS-RE). Specifically, authors always omit the Background Knowledge (BK) that they assume is well known by readers, but would be essential for a machine to identify relationships. To address this issue, in this work, we assume that the reasoning paths between entity pairs over a knowledge graph could be utilized as BK to fill the "gaps" in text and thus facilitate DS-RE. Experimental results prove the effectiveness of the reasoning paths for DS-RE, because the proposed model that incorporates the reasoning paths achieves significant and consistent improvements as compared with a state-of-the-art DS-RE model.