CoRI: Collective Relation Integration with Data Augmentation for Open Information Extraction

被引:0
|
作者
Jiang, Zhengbao [1 ]
Han, Jialong [2 ]
Sisman, Bunyamin [2 ]
Dong, Xin Luna [2 ]
机构
[1] Carnegie Mellon Univ, Language Technol Inst, Pittsburgh, PA 15213 USA
[2] Amazon, Seattle, WA USA
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Integrating extracted knowledge from the Web to knowledge graphs (KGs) can facilitate tasks like question answering. We study relation integration that aims to align free-text relations in subject-relation-object extractions to relations in a target KG. To address the challenge that free-text relations are ambiguous, previous methods exploit neighbor entities and relations for additional context. However, the predictions are made independently, which can be mutually inconsistent. We propose a two-stage Collective Relation Integration (CoRI) model, where the first stage independently makes candidate predictions, and the second stage employs a collective model that accesses all candidate predictions to make globally coherent predictions. We further improve the collective model with augmented data from the portion of the target KG that is otherwise unused. Experiment results on two datasets show that CoRI can significantly outperform the baselines, improving AUC from .677 to .748 and from .716 to .780, respectively.
引用
收藏
页码:4706 / 4716
页数:11
相关论文
共 50 条
  • [1] Few-shot biomedical relation extraction using data augmentation and domain information
    Guo, Bocheng
    Zhao, Di
    Dong, Xin
    Meng, Jiana
    Lin, Hongfei
    NEUROCOMPUTING, 2024, 595
  • [2] Leveraging Data Augmentation for Process Information Extraction
    Neuberger, Julian
    Doll, Leonie
    Engelmann, Benedikt
    Ackermann, Lars
    Jablonski, Stefan
    ENTERPRISE, BUSINESS-PROCESS AND INFORMATION SYSTEMS MODELING, BPMDS 2024, EMMSAD 2024, 2024, 511 : 57 - 70
  • [3] An Open Relation Extraction System for Web Text Information
    Li, Huagang
    Liu, Bo
    APPLIED SCIENCES-BASEL, 2022, 12 (11):
  • [4] Entity relation extraction in the medical domain: based on data augmentation
    Wang, Anli
    Li, Linyi
    Wu, Xuehong
    Zhu, Jianping
    Yu, Shanshan
    Chen, Xi
    Li, Jianhua
    Zhu, Hongtao
    ANNALS OF TRANSLATIONAL MEDICINE, 2022, 10 (19)
  • [5] GDA: Generative Data Augmentation Techniques for Relation Extraction Tasks
    Hu, Xuming
    Liu, Aiwei
    Tan, Zeqi
    Zhang, Xin
    Zhang, Chenwei
    King, Irwin
    Yu, Philip S.
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2023), 2023, : 10221 - 10234
  • [6] MODELS OF DATA INTEGRATION IN OPEN INFORMATION SYSTEMS
    Berko, A. Y.
    ACTUAL PROBLEMS OF ECONOMICS, 2010, (112): : 147 - 152
  • [7] FREDA: Few-Shot Relation Extraction Based on Data Augmentation
    Liu, Junbao
    Qin, Xizhong
    Ma, Xiaoqin
    Ran, Wensheng
    APPLIED SCIENCES-BASEL, 2023, 13 (14):
  • [8] Combining information extraction and data integration in the ESTEST system
    Williams, Dean
    Poulovassilis, Alexandra
    ICSOFT 2006: PROCEEDINGS OF THE FIRST INTERNATIONAL CONFERENCE ON SOFTWARE AND DATA TECHNOLOGIES, VOL 2, 2006, : 13 - +
  • [9] A mutually beneficial integration of data mining and information extraction
    Nahm, UY
    Mooney, RJ
    SEVENTEENTH NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE (AAAI-2001) / TWELFTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE (IAAI-2000), 2000, : 627 - 632
  • [10] Combining Information Extraction and Data Integration in the ESTEST system
    Williams, Dean
    Poulovassilis, Alexandra
    SOFTWARE AND DATA TECHNOLOGIES, 2008, 10 : 279 - 292