文献类型：期刊文献

英文题名：A Bidirectional Extraction-Then-Evaluation Framework for Complex Relation Extraction

作者：Zhang, Weiyan[1];Wang, Jiacheng[1];Chen, Chuang[1];Lu, Wanpeng[1];Du, Wen[2];Wang, Haofen[3];Liu, Jingping[1];Ruan, Tong[1]

机构：[1]East China Univ Sci & Technol, Sch Informat Sci & Engn, Shanghai 200237, Peoples R China;[2]DS Informat Technol Co Ltd, Res & Dev Dept, Shanghai 200032, Peoples R China;[3]Tongji Univ, Coll Design & Innovat, Shanghai 200092, Peoples R China

年份：2024

卷号：36

期号：12

起止页码：7442

外文期刊名：IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING

收录：;EI(收录号：20243216813682);WOS:【SCI-EXPANDED(收录号:WOS:001354743800008)】；

基金：This work was supported in part by the National Natural Science Foundation of China under Grant 62306112, in part by Shanghai Sailing Program under Grant 23YF1409400, and in part by the Shanghai Pilot Program for Basic Research under Grant 22TQ1400100-20. Recommended for acceptance by T. Weninger.

语种：英文

外文关键词：Data mining; Feature extraction; Task analysis; Pipelines; Object oriented modeling; Iterative methods; Large language models; Complex relation extraction; extraction-then-evaluation; information extraction

摘要：Relation extraction is an important task in the field of natural language processing. Previous works mainly focus on adopting pipeline methods or joint methods to model relation extraction in general scenarios. However, these existing methods face challenges when adapting to complex relation extraction scenarios, such as handling overlapped triplets, multiple triplets, and cross-sentence triplets. In this paper, we revisit the advantages and disadvantages of the aforementioned methods in complex relation extraction. Based on the in-depth analysis, we propose a novel two-stage bidirectional extract-then-evaluate framework named BeeRe. In the extraction stage, we first obtain the subject set, relation set, and object set. Then, we design subject- and object-oriented triplet extractors to iteratively recurrent obtain candidate triplets, ensuring high recall. In the evaluation stage, we adopt a relation-oriented triplet filter to determine subject-object pairs based on relations in triplets obtained in the first stage, ensuring high precision. We conduct extensive experiments on three public datasets to show that BeeRe achieves state-of-the-art performance in both complex and general relation extraction scenarios. Even when compared to large language models like closed-source/open-source LLMs, BeeRe still has significant performance gains.