A Two-Phase Paradigm for Joint Entity-Relation Extraction
作者机构:College of ComputerNational University of Defense TechnologyChangsha410073China The Affiliated Eye Hospital of Nanjing Medical UniversityNanjing210029China
出 版 物:《Computers, Materials & Continua》 (计算机、材料和连续体(英文))
年 卷 期:2023年第74卷第1期
页 面:1303-1318页
核心收录:
学科分类:08[工学] 0812[工学-计算机科学与技术(可授工学、理学学位)]
基 金:supported by the National Key Research and Development Program[2020YFB1006302]
主 题:Joint extraction span-based named entity recognition relation extraction data distribution global features
摘 要:An exhaustive study has been conducted to investigate span-based models for the joint entity and relation extraction ***,these models sample a large number of negative entities and negative relations during the model training,which are essential but result in grossly imbalanced data distributions and in turn cause suboptimal model *** order to address the above issues,we propose a two-phase paradigm for the span-based joint entity and relation extraction,which involves classifying the entities and relations in the first phase,and predicting the types of these entities and relations in the second *** two-phase paradigm enables our model to significantly reduce the data distribution gap,including the gap between negative entities and other entities,aswell as the gap between negative relations and other *** addition,we make the first attempt at combining entity type and entity distance as global features,which has proven effective,especially for the relation *** results on several datasets demonstrate that the span-based joint extraction model augmented with the two-phase paradigm and the global features consistently outperforms previous state-ofthe-art span-based models for the joint extraction task,establishing a new standard *** and quantitative analyses further validate the effectiveness the proposed paradigm and the global features.