Conference
Open access
2026
ATGL: An Adaptive-Threshold Global Loss for Document-level Relation Extraction
The ATGL serves as a general optimization objective that can be readily applied to different DocRE models and outperforms other DocRE losses and achieves state-of-the-art results, while consistently improving the performance of existing DocRE models.
Huangming Xu, Fu Zhang, Zhixuan Yang et al.
· Annual Meeting of the Associ... · 0 citations