A Prompt-Based Method with Multi-View Optimization for Open Relation Extraction

Abstract

Open Relation Extraction (OpenRE) is a task that involves discovering new relation types by referring to labeled instances. Existing methods mainly rely on large pre-trained models to obtain the relation representation of entity pairs, and then jointly train the supervised and unsupervised data using a joint loss function. Some researchers enhance their relation representation by introducing additional information as prompt. However, these approaches have several major issues. Firstly, many of them rely on external knowledge bases, which require a large amount of high-quality data. Secondly, They fail to consider the rich semantic and prior knowledge existing in the labels. To this end, we propose a novel method to incorporate the prior knowledge into prompt-tuning and introduce a multi-view algorithm to optimize the relation representations. We conduct experiments on two common datasets, and the results show that our proposed method significantly outperforms the previous state-of-the-art methods.