作者位次 #4/5ACL 2026Poster· Natural Language Processing
ATGL : An Adaptive-Threshold Global Loss for Document-level Relation Extraction
Huangming Xu · Fu Zhang · Zhixuan Yang · Lu Zhang · Jingwei Cheng
摘要
Document-level relation extraction (DocRE) aims to determine which relations hold between a given entity pair within a document. As a multi-label classification task, the most commonly adopted paradigm introduces a learnable threshold to distinguish positive and negative classes for an entity pai...