Adversarial Training Improved Multi-Path Multi-Scale Relation Detector for Knowledge Base Question Answering

被引:3
作者
Zhang, Yanan [1 ,2 ,3 ]
Xu, Guangluan [1 ,3 ]
Fu, Xingyu [1 ,3 ]
Jin, Li [1 ,3 ]
Huang, Tingle [4 ]
机构
[1] Chinese Acad Sci, Inst Elect, Beijing 100190, Peoples R China
[2] Univ Chinese Acad Sci, Sch Elect Elect & Commun Engn, Beijing 100190, Peoples R China
[3] Chinese Acad Sci, Inst Elect, Key Lab Network Informat Syst Technol NIST, Beijing 100190, Peoples R China
[4] Chinese Acad Sci, Inst Software, Beijing 100190, Peoples R China
关键词
Adversarial training; knowledge base question answering; relation detection;
D O I
10.1109/ACCESS.2020.2984393
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Knowledge Base Question Answering (KBQA) is a promising approach for users to access substantial knowledge and has become a research focus in recent years. Our paper focuses on relation detection, a subtask of KBQA and proposes an adversarial training improved multi-path multi-scale relation detector (AdvT-MMRD) to improve the performance of a common KBQA system. To solve the problem of matching the casual form of a question with the logical form of a predicate, we use question pattern-relation matching, in which an attention-based bidirectional recurrent neural network with gated recurrent units (Bi-GRUs) is used to match semantic similarity and a convolutional neural network (CNN) is used to learn literal similarity between question and relation. We also explore two ways to measure the relevance of entity type-relation pairs through several level representations. Additionally, an adversarial training strategy is conducted to enhance our model. The experimental results demonstrate that our approach not only achieves a state-of-the-art accuracy of 93.8 & x0025; on relation detection task, but contributes our KBQA system to reaching an outstanding accuracy of 79.0 & x0025; on the SimpleQuestions benchmark.
引用
收藏
页码:63310 / 63319
页数:10
相关论文
共 11 条
  • [1] Translational relation embeddings for multi-hop knowledge base question answering
    Li, Ziyan
    Wang, Haofen
    Zhang, Wenqiang
    JOURNAL OF WEB SEMANTICS, 2022, 74
  • [2] Relation Extraction as Text Matching: A Scheme for Multi-hop Knowledge Base Question Answering
    Li, Ziyan
    Ni, Kan
    Wang, Haofen
    Zhang, Wenqiang
    CCKS 2022 - EVALUATION TRACK, 2022, 1711 : 191 - 201
  • [3] Image Dehazing Algorithm Based on Multi-Scale Fusion and Adversarial Training
    Liu Yuhang
    Shuai, Wu
    LASER & OPTOELECTRONICS PROGRESS, 2020, 57 (06)
  • [4] Multi-hop Knowledge Base Question Answering with an Iterative Sequence Matching Model
    Lan, Yunshi
    Wang, Shuohang
    Jiang, Jing
    2019 19TH IEEE INTERNATIONAL CONFERENCE ON DATA MINING (ICDM 2019), 2019, : 359 - 368
  • [5] A dynamic graph expansion network for multi-hop knowledge base question answering
    Wu, Wenqing
    Zhu, Zhenfang
    Qi, Jiangtao
    Wang, Wenling
    Zhang, Guangyuan
    Liu, Peiyu
    NEUROCOMPUTING, 2023, 515 : 37 - 47
  • [6] Improving Multi-hop Knowledge Base Question Answering by Learning Intermediate Supervision Signals
    He, Gaole
    Lan, Yunshi
    Jiang, Jing
    Zhao, Wayne Xin
    Wen, Ji-Rong
    WSDM '21: PROCEEDINGS OF THE 14TH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING, 2021, : 535 - 543
  • [7] Chinese Knowledge Base Question Answering by Attention-Based Multi-Granularity Model
    Shen, Cun
    Huang, Tinglei
    Liang, Xiao
    Li, Feng
    Fu, Kun
    INFORMATION, 2018, 9 (04)
  • [8] Adversarial Training Collaborating Multi-Path Context Feature Aggregation Network for Maize Disease Density Prediction
    Yang, Wei
    Shen, Peiquan
    Ye, Zhaoyi
    Zhu, Zhongmin
    Xu, Chuan
    Liu, Yi
    Mei, Liye
    PROCESSES, 2023, 11 (04)
  • [9] Adversarial training of multi-scale channel attention network for enhanced robustness in bearing fault diagnosis
    Peng, Haotian
    Du, Jinsong
    Gao, Jie
    Wang, Yu
    Wang, Wei
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2024, 35 (05)
  • [10] Complex Knowledge Base Question Answering for Intelligent Bridge Management Based on Multi-Task Learning and Cross-Task Constraints
    Yang, Xiaoxia
    Yang, Jianxi
    Li, Ren
    Li, Hao
    Zhang, Hongyi
    Zhang, Yue
    ENTROPY, 2022, 24 (12)