"CREAM: Named Entity Recognition with Concise query and REgion-Aware Mi" by Xun Yao, Qihang Yang et al.
Recent advancements in Machine Reading Comprehension (MRC) models have sparked interest in the field of Named Entity Recognition (NER), where entities are extracted as answers of given queries. Yet, existing MRC-based models face several challenges, including high computational costs, limited consideration of entity content information, and the tendency to generate sharp boundaries, that hinder their generalizability. To alleviate these issues, this paper introduces CREAM, an enhanced model leveraging Concise query and REgion-Aware Minimization. First, we propose a simple yet effective strateg...
Source: uow.edu.au
