Self-Supervised Commonsense Knowledge Learning for Document-Level Relation Extraction

Compared to sentence-level relation extraction, practical document-level relation extraction (DocRE) is a more challenging task for which multi-entity problems need to be resolved. It aims at extracting relationships between two entities over multiple sentences at once while taking into account significant cross-sentence features. Learning long-distance semantic relation representation across sentences in a document, however, is a widespread and difficult task. To address this problem, this paper proposes a self-supervised commonsense-enhanced DocRE method, called SCDRE, without external knowledge. First, we introduce self-supervised learning to represent commonsense knowledge of each entity in an entity pair based on the commonsense entailed text. Second, we convert the cross-sentence entity pairs into anonymous entity pairs with coreference commonsense replacement. Finally, we perform semantic relation representation learning on the anonymous entity pairs and automatically convert them into target entity pairs. We examined our model on three publicly accessible datasets, DocRED, DialogRE and MPDD, and the results show that it performs significantly better than strong baselines by 2.03% F1, and commonsense knowledge has an important contribution to the DocRE by the ablation experimental analysis.