English

Integrating Graph Contextualized Knowledge into Pre-trained Language Models

Computation and Language 2021-10-01 v3 Artificial Intelligence

Abstract

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.

Keywords

Cite

@article{arxiv.1912.00147,
  title  = {Integrating Graph Contextualized Knowledge into Pre-trained Language Models},
  author = {Bin He and Di Zhou and Jinghui Xiao and Xin jiang and Qun Liu and Nicholas Jing Yuan and Tong Xu},
  journal= {arXiv preprint arXiv:1912.00147},
  year   = {2021}
}

Comments

Findings of EMNLP 2020

R2 v1 2026-06-23T12:31:47.804Z