Document-level relation extraction with graph neural networks faces a
fundamental graph construction gap between training and inference - the golden
graph structure only available during training, which causes that most methods
adopt heuristic or syntactic rules to construct a prior graph as a pseudo
proxy. In this paper, we propose $\textbf{ConstGCN}$, a novel graph
convolutional network which performs knowledge-based information propagation
between entities along with all specific relation spaces without any prior
graph construction. Specifically, it updates the entity representation by
aggregating information from all other entities along with each relation space,
thus modeling the relation-aware spatial information. To control the
information flow passing through the indeterminate relation spaces, we propose
to constrain the propagation using transmitting scores learned from the Noise
Contrastive Estimation between fact triples. Experimental results show that our
method outperforms the previous state-of-the-art (SOTA) approaches on the DocRE
dataset.

本文提出 ConstGCN 模型，利用基于知识的信息传播不需要事先构建图来解决训练和推理之间的图构建鸿沟，性能优于先前的最先进方法。