Integrating Graph Contextualized Knowledge into Pre-trained Language Models
This work addresses the need for better knowledge integration in NLP for medical applications, though it appears incremental as it builds on existing transformer and KRL methods.
The paper tackled the problem of knowledge representation learning (KRL) by incorporating graph contextualized information from knowledge graphs, rather than treating triples in isolation, and achieved state-of-the-art performance on medical NLP tasks with improvements over TransE.
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.