Relation Discovery with Out-of-Relation Knowledge Base as Supervision
This addresses the challenge of leveraging existing knowledge bases for relation discovery in NLP, though it is incremental by extending unsupervised methods with external constraints.
The paper tackles the problem of discovering unseen relations from text using out-of-relation knowledge bases as supervision, and the result shows that their approach improves state-of-the-art performance by a large margin.
Unsupervised relation discovery aims to discover new relations from a given text corpus without annotated data. However, it does not consider existing human annotated knowledge bases even when they are relevant to the relations to be discovered. In this paper, we study the problem of how to use out-of-relation knowledge bases to supervise the discovery of unseen relations, where out-of-relation means that relations to discover from the text corpus and those in knowledge bases are not overlapped. We construct a set of constraints between entity pairs based on the knowledge base embedding and then incorporate constraints into the relation discovery by a variational auto-encoder based algorithm. Experiments show that our new approach can improve the state-of-the-art relation discovery performance by a large margin.