作者位次 #10/10ACL 2026Findings· Findings of ACL
Memory-Guided Hard Data Augmentation for Multimodal Named Entity Recognition
Xinyu Liu · Kai fu · Yinghan Shi · Quanyou Chu · Ming Du · Hongya Wang · Xiaojun Meng · Jiansheng Wei · Yanghua Xiao · Bo Xu
摘要
Multimodal Named Entity Recognition relies on visual context to resolve textual ambiguities. To mitigate data scarcity, Data Augmentation (DA) has become a standard practice; however, existing methods predominantly adopt a one-size-fits-all and random perturbation paradigm, ignoring the internal...