Compositional Learning of Embeddings for Relation Paths in Knowledge Base and Text

摘要: Modeling relation paths has offered significant gains in embedding models for knowledge base (KB) completion. However, enumerating between two entities is very expensive, and existing approaches typically resort to approximation with a sampled subset. This problem particularly acute when text jointly modeled KB relations used provide direct evidence facts mentioned it. In this paper, we propose the first exact dynamic programming algorithm which enables efficient incorporation of all bounded length, while modeling both types intermediate nodes compositional path representations. We conduct theoretical analysis efficiency gain from approach. Experiments on datasets show that it addresses representational limitations prior improves accuracy