Knowledge Graph Representation with Jointly Structural and Textual Encoding
This work addresses the limitation of existing methods that rely solely on structural information, which struggle with new or sparsely connected entities, by incorporating textual descriptions to improve representation learning for knowledge graphs.
The paper tackled the problem of knowledge graph embedding by proposing a novel deep architecture that integrates both structural and textual information, resulting in models that outperform baselines on link prediction and triplet classification tasks.
The objective of knowledge graph embedding is to encode both entities and relations of knowledge graphs into continuous low-dimensional vector spaces. Previously, most works focused on symbolic representation of knowledge graph with structure information, which can not handle new entities or entities with few facts well. In this paper, we propose a novel deep architecture to utilize both structural and textual information of entities. Specifically, we introduce three neural models to encode the valuable information from text description of entity, among which an attentive model can select related information as needed. Then, a gating mechanism is applied to integrate representations of structure and text into a unified architecture. Experiments show that our models outperform baseline by margin on link prediction and triplet classification tasks. Source codes of this paper will be available on Github.