Modeling Relation Paths for Representation Learning of Knowledge Bases
This work addresses the challenge of improving knowledge base embeddings for tasks like completion and relation extraction, offering a novel approach that leverages relation paths, though it is incremental in building upon existing translation-based methods.
The paper tackles the problem of representation learning for knowledge bases by incorporating multiple-step relation paths, not just direct relations, to capture richer inference patterns. It introduces a path-based model that uses a path-constraint resource allocation algorithm to measure reliability and semantic composition of relation embeddings, achieving significant and consistent improvements on knowledge base completion and relation extraction tasks.
Representation learning of knowledge bases (KBs) aims to embed both entities and relations into a low-dimensional space. Most existing methods only consider direct relations in representation learning. We argue that multiple-step relation paths also contain rich inference patterns between entities, and propose a path-based representation learning model. This model considers relation paths as translations between entities for representation learning, and addresses two key challenges: (1) Since not all relation paths are reliable, we design a path-constraint resource allocation algorithm to measure the reliability of relation paths. (2) We represent relation paths via semantic composition of relation embeddings. Experimental results on real-world datasets show that, as compared with baselines, our model achieves significant and consistent improvements on knowledge base completion and relation extraction from text.