An Open Relation Extraction System for Web Text Information

Web texts typically undergo the open-ended growth of new relations. Traditional relation extraction methods lack automatic annotation and perform poorly on new relation extraction tasks. We propose an open-domain relation extraction system (ORES) based on distant supervision and few-shot learning to solve this problem. More specifically, we utilize tBERT to design instance selector 1, implementing automatic labeling in the data mining component. Meanwhile, we design example selector 2 based on K-BERT in the new relation extraction component. The real-time data management component outputs new relational data. Experiments show that ORES can filter out higher quality and diverse instances for better new relation learning. It achieves significant improvement compared to Neural Snowball with fewer seed sentences.