We target on the document-level relation extraction in an end-to-end setting,
where the model needs to jointly perform mention extraction, coreference
resolution (COREF) and relation extraction (RE) at once, and gets evaluated in
an entity-centric way. Especially, we address the two-way interaction between
COREF and RE that has not been the focus by previous work, and propose to
introduce explicit interaction namely Graph Compatibility (GC) that is
specifically designed to leverage task characteristics, bridging decisions of
two tasks for direct task interference. Our experiments are conducted on DocRED
and DWIE; in addition to GC, we implement and compare different multi-task
settings commonly adopted in previous work, including pipeline, shared
encoders, graph propagation, to examine the effectiveness of different
interactions. The result shows that GC achieves the best performance by up to
2.3/5.1 F1 improvement over the baseline.

本研究基于一种端到端的设置，同时执行提及提取，共指解决和关系提取，并在实体为中心的评估中进行文档级别的关系提取，特别是解决了以前工作未考虑的共指解决和关系提取之间的交互问题，并提出了显式交互，即图兼容性，以发挥任务特征的作用，通过相互作用的决策来弥合两个任务。本实验证明了该方法的有效性，并取得了比基线高 2.3/5.1 F1 改进的最优性能。