有监督实体关系联合抽取方法研究综述

被引:62
作者
张少伟 [1 ]
王鑫 [1 ,2 ]
陈子睿 [1 ]
王林 [3 ]
徐大为 [3 ]
贾勇哲 [1 ,3 ]
机构
[1] 天津大学智能与计算学部
[2] 天津市认知计算与应用重点实验室
[3] 天津泰凡科技有限公司
关键词
联合抽取; 特征工程; 神经网络;
D O I
暂无
中图分类号
TP391.1 [文字信息处理];
学科分类号
120506 [数字人文];
摘要
实体关系联合抽取作为信息抽取领域的核心任务,能够从非结构化或半结构化的文本中自动识别实体、实体类型以及实体之间特定的关系类型,为知识图谱构建、智能问答和语义搜索等下游任务提供基础支持。传统的流水线方法将实体关系联合抽取分解成命名实体识别和关系抽取两个独立的子任务,由于两个子任务之间缺少交互,流水线方法存在误差传播等问题。近年来,实体关系联合抽取成为新的研究趋势,其可以建立统一的模型使得不同子任务彼此交互,进一步提升模型性能。对有监督实体关系联合抽取方法进行综述,根据抽取特征的不同方式,可将实体关系联合抽取分为基于特征工程的联合抽取和基于神经网络的联合抽取两种类型。首先,介绍基于特征工程的联合抽取,包括整数线性规划、卡片金字塔解析、概率图模型和结构化预测四种方法,这四种方法都需要采用相对复杂的特征工程方法。然后,介绍基于神经网络的联合抽取,这类方法可以自动抽取特征信息,已逐渐成为联合抽取的主流方法,其主要包括共享参数和联合解码两种类型。接着,介绍有监督实体关系联合抽取常用的七个数据集以及评价指标,并对不同的实体关系联合抽取方法进行了实验对比分析。最后,展望实体关系联合抽取的未来研究方向。
引用
收藏
页码:713 / 733
页数:21
相关论文
共 26 条
[1]
CopyMTL: Copy Mechanism for Joint Extraction of Entities and Relations with Multi-Task Learning.[J].Daojian Zeng;Haoran Zhang;Qianying Liu.Proceedings of the AAAI Conference on Artificial Intelligence.2020, 05
[2]
Effective Modeling of Encoder-Decoder Architecture for Joint Entity and Relation Extraction.[J].Tapas Nayak;Hwee Tou Ng.Proceedings of the AAAI Conference on Artificial Intelligence.2020, 05
[3]
Jointly Extracting Multiple Triplets with Multilayer Translation Constraints.[J].Zhen Tan;Xiang Zhao;Wei Wang;Weidong Xiao.Proceedings of the AAAI Conference on Artificial Intelligence.2019,
[4]
Span-based Joint Entity and Relation Extraction with Transformer Pre-training..[J].Markus Eberts;Adrian Ulges.CoRR.2019,
[5]
A Deep Neural Network Model for Joint Entity and Relation Extraction [J].
Pang, Yihe ;
Liu, Jie ;
Liu, Lizhen ;
Yu, Zhengtao ;
Zhang, Kai .
IEEE ACCESS, 2019, 7 :179143-179150
[6]
Joint Extraction of Entities and Relations Based on a Novel Decomposition Strategy..[J].Bowen Yu;Zhenyu Zhang;Jianlin Su;Yubin Wang;Tingwen Liu;Bin Wang;Sujian Li.CoRR.2019,
[7]
Joint entity recognition and relation extraction as a multi-head selection problem.[J].Giannis Bekoulis;Johannes Deleu;Thomas Demeester;Chris Develder.Expert Systems With Applications.2018,
[8]
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation [J].
Gatt, Albert ;
Krahmer, Emiel .
JOURNAL OF ARTIFICIAL INTELLIGENCE RESEARCH, 2018, 61 :65-170
[9]
Joint Extraction of Entities and Relations Using Reinforcement Learning and Deep Learning [J].
Feng, Yuntian ;
Zhang, Hongjun ;
Hao, Wenning ;
Chen, Gang .
COMPUTATIONAL INTELLIGENCE AND NEUROSCIENCE, 2017, 2017
[10]
A neural joint model for entity and relation extraction from biomedical text [J].
Li, Fei ;
Zhang, Meishan ;
Fu, Guohong ;
Ji, Donghong .
BMC BIOINFORMATICS, 2017, 18