Knowledge Graph Representation with Jointly Structural and Textual Encoding

Knowledge Graph Representation with Jointly Structural and Textual Encoding

Jiacheng Xu, Xipeng Qiu, Kan Chen, Xuanjing Huang

Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence
Main track. Pages 1318-1324. https://doi.org/10.24963/ijcai.2017/183

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 and obtain state-of-the-art results on link prediction and triplet classification tasks.
Keywords:
Knowledge Representation, Reasoning, and Logic: Knowledge Representation Languages
Machine Learning: Deep Learning
Machine Learning: Knowledge-based Learning
Natural Language Processing: NLP Applications and Tools