An updated method for link prediction that uses a regularization factor that models relation argument types

Abstract (Kotnis and Nastase, 2017): Learning relations based on evidence from knowledge repositories relies on processing the available relation instances. Knowledge repositories are not balanced in terms of relations or entities – there are relations with less than 10 but also thousands of instances, and entities involved in less than 10 but also thousands of relations. Many relations, however, have clear domain and range, which we hypothesize could help learn a better, more generalizing, model. We include such information in the RESCAL model in the form of a regularization factor added to the loss function that takes into account the types (categories) of the entities that appear as arguments to relations in the knowledge base. Tested on Freebase, a frequently used benchmarking dataset for link/path predicting tasks, we note increased performance compared to the baseline model in terms of mean reciprocal rank and hits@N, N = 1, 3, 10. Furthermore, we discover scenarios that significantly impact the effectiveness of the type regularizer.