“…Since self-training methods (Rosenberg et al, 2005) accumulate noise in pseudo labels (Hu et al, 2021b), some methods (Han et al, 2018;Lin et al, 2019) Ye and Ling, 2019). Recently, language models has shown their ability on various tasks based on prompting (Li et al, 2022a(Li et al, ,b, 2021Lu et al, 2023). Since the scale of KB is limited, PRBOOST (Zhang et al, 2022) asks PLM by prompt to predict the relation directly and take the predictions as rules.…”