Ruoyu Zhang's paper " A Novel Table-to-Graph Generation Approach for Document-Level Joint Entity and Relation Extraction" has been accepted by ACL 2023.

Document-level relation extraction (DocRE) aims to extract relations among entities within a document, which is crucial for applications like knowledge graph construction. Existing methods usually assume that entities and their mentions are identified beforehand, which falls short of real-world applications. To overcome this limitation, we propose TaG, a novel table-to-graph generation model for joint extraction of entity and relation at document-level. To enhance the learning of task dependencies, TaG induces a latent graph among mentions, with different types of edges indicating different task information, which is further broadcast with a relational graph convolutional network. To alleviate the error propagation problem, we adapt the hierarchical agglomerative clustering algorithm to back propagate task information at decoding stage. Experiments on the benchmark dataset, DocRED, demonstrate that TaG outperforms previous baseline by a large margin and achieve state-of-the-art results.