Modeling Relation Paths for Representation Learning of Knowledge Bases

摘要: Representation learning of knowledge bases aims to embed both entities and relations into a low-dimensional space. Most existing methods only consider direct in representation learning. We argue that multiple-step relation paths also contain rich inference patterns between entities, propose path-based model. This model considers as translations for learning, addresses two key challenges: (1) Since not all are reliable, we design path-constraint resource allocation algorithm measure the reliability paths. (2) represent via semantic composition embeddings. Experimental results on real-world datasets show that, compared with baselines, our achieves significant consistent improvements base completion extraction from text. The source code this paper can be obtained https://github.com/mrlyk423/ relation_extraction.