Entity Retrieval in the Knowledge Graph with Hierarchical Entity Type and Content

We investigate the task of ad-hoc entity retrieval from a knowledge graph with hierarchical entity types and entity descriptions. Our model directly encodes them into a Markov random field based framework via a path aware smoothing method. We conduct experiments on recent benchmark datasets and investigate the incorporation of the Wikipedia type and article information. The results show that our framework achieves improvements over the existing and state-of-the-art models.