Integrating Graph Contextualized Knowledge into Pre-trained Language Models

Xin Jiang, Tong Xu, Jinghui Xiao, Liu, Qun, Nicholas Jing Yuan, Bin He, Di Zhou
2019-11-30

SCID:  54.1/zwna6byy
Complex node interactions are common in knowledge graphs, and these interactions also contain rich knowledge information. However, traditional methods usually treat a triple as a training unit during the knowledge representation learning (KRL) procedure, neglecting contextualized information of the nodes in knowledge graphs (KGs). We generalize the modeling object to a very general form, which theoretically supports any subgraph extracted from the knowledge graph, and these subgraphs are fed into a novel transformer-based model to learn the knowledge embeddings. To broaden usage scenarios of knowledge, pre-trained language models are utilized to build a model that incorporates the learned knowledge representations. Experimental results demonstrate that our model achieves the state-of-the-art performance on several medical NLP tasks, and improvement above TransE indicates that our KRL method captures the graph contextualized information effectively.
Publication Details
Publication Date
2019-11-30
Journal
Publisher
ISSN
Access Type
Author Information
Authors
Xin Jiang
Tong Xu
Jinghui Xiao
Liu, Qun
Nicholas Jing Yuan
Bin He
Di Zhou
Explore More Research
Use the citation graph to discover related papers and expand your research horizons.
Click any node to explore
Download PDF
100%