A Densely Connected Criss-Cross Attention Network for Document-level Relation Extraction

26 Mar 2022  ·  Liang Zhang, Yidong Cheng ·

Document-level relation extraction (RE) aims to identify relations between two entities in a given document. Compared with its sentence-level counterpart, document-level RE requires complex reasoning. Previous research normally completed reasoning through information propagation on the mention-level or entity-level document-graph, but rarely considered reasoning at the entity-pair-level.In this paper, we propose a novel model, called Densely Connected Criss-Cross Attention Network (Dense-CCNet), for document-level RE, which can complete logical reasoning at the entity-pair-level. Specifically, the Dense-CCNet performs entity-pair-level logical reasoning through the Criss-Cross Attention (CCA), which can collect contextual information in horizontal and vertical directions on the entity-pair matrix to enhance the corresponding entity-pair representation. In addition, we densely connect multiple layers of the CCA to simultaneously capture the features of single-hop and multi-hop logical reasoning.We evaluate our Dense-CCNet model on three public document-level RE datasets, DocRED, CDR, and GDA. Experimental results demonstrate that our model achieves state-of-the-art performance on these three datasets.

PDF Abstract

Datasets


Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Relation Extraction CDR Dense-CCNet-SciBERTbase F1 77.06 # 2
Relation Extraction DocRED Dense-CCNet-BERTbase F1 62.55 # 13
Ign F1 60.46 # 13
Relation Extraction GDA Dense-CCNet-SciBERTbase F1 86.44 # 2

Methods


No methods listed for this paper. Add relevant methods here