关系抽取
计算机科学
嵌入
人工智能
可解释性
关系(数据库)
领域(数学分析)
代表(政治)
公制(单位)
自然语言处理
机器学习
语义学(计算机科学)
一般化
水准点(测量)
信息抽取
数据挖掘
数学
数学分析
运营管理
大地测量学
政治
政治学
法学
经济
程序设计语言
地理
作者
Zhongju Yuan,Zhenkun Wang,Genghui Li
标识
DOI:10.1109/ijcnn54540.2023.10191836
摘要
Few-shot relation extraction aims to recognize novel relations with few labeled sentences in each relation. Previous metric-based few-shot relation extraction algorithms identify relationships by comparing the prototypes generated by the few labeled sentences embedding with the embeddings of the query sentences using a trained metric function. However, as these domains always have considerable differences from those in the training dataset, the generalization ability of these approaches on unseen relations in many domains is limited. Since the prototype is necessary for obtaining relationships between entities in the latent space, we suggest learning more interpretable and efficient prototypes from prior knowledge and the intrinsic semantics of relations to extract new relations in various domains more effectively. By exploring the relationships between relations using prior information, we effectively improve the prototype representation of relations. By using contrastive learning to make the classification margins between sentence embedding more distinct, the prototype's geometric interpretability is enhanced. Additionally, utilizing a transfer learning approach for the cross-domain problem allows the generation process of the prototype to account for the gap between other domains, making the prototype more robust and enabling the better extraction of associations across multiple domains. The experiment results on the benchmark FewRel dataset demonstrate the advantages of the suggested method over some state-of-the-art approaches.
科研通智能强力驱动
Strongly Powered by AbleSci AI