ProSyno: context-free prompt learning for synonym discovery
摘要
Synonym discovery is important in a wide variety of concept-related tasks, such as entity/concept mining and industrial knowledge graph (KG) construction. It intends to determine whether two terms refer to the same concept in semantics. Existing methods rely on contexts or KGs. However, these methods are often impractical in some cases where contexts or KGs are not available. Therefore, this paper proposes a context-free prompt learning based synonym discovery method called ProSyno, which takes the world’s largest freely available dictionary Wiktionary as a semantic source. Based on a pre-trained language model (PLM), we employ a prompt learning method to generalize to other datasets without any fine-tuning. Thus, our model is more appropriate for context-free situation and can be easily transferred to other fields. Experimental results demonstrate its superiority comparing with state-of-the-art methods.