Multi-Target Stance Detection via a Dynamic Memory-Augmented Network

被引:27
|
作者
Wei, Penghui [1 ]
Lin, Junjie
Mao, Wenji
机构
[1] Chinese Acad Sci, Inst Automat, SKLMCCS, Beijing, Peoples R China
来源
基金
国家重点研发计划;
关键词
D O I
10.1145/3209978.3210145
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Stance detection aims at inferring from text whether the author is in favor of, against, or neutral towards a target entity. Most of the existing studies consider different target entities separately. However, in many scenarios, stance targets are closely related, such as several candidates in a general election and different brands of the same product. Multi-target stance detection, in contrast, aims at jointly detecting stances towards multiple related targets. As stance expression regarding a target can provide additional information to help identify the stances towards other related targets, modeling expressions regarding multiple targets jointly is beneficial for improving the overall performance compared to single-target scheme. In this paper, we propose a dynamic memory-augmented network DMAN for multi-target stance detection. DMAN utilizes a shared external memory, which is dynamically updated through the learning process, to capture and store stance-indicative information for multiple related targets. It then jointly predicts stances towards these targets in a multitask manner. Experimental results on a benchmark dataset show the effectiveness of DMAN.
引用
收藏
页码:1229 / 1232
页数:4
相关论文
共 50 条
  • [1] Stance Detection with a Multi-Target Adversarial Attention Network
    Sun, Qingying
    Xi, Xuefeng
    Sun, Jiajun
    Wang, Zhongqing
    Xu, Huiyan
    [J]. ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING, 2023, 22 (02)
  • [2] A Cognitive Memory-Augmented Network for Visual Anomaly Detection
    Wang, Tian
    Xu, Xing
    Shen, Fumin
    Yang, Yang
    [J]. IEEE-CAA JOURNAL OF AUTOMATICA SINICA, 2021, 8 (07) : 1296 - 1307
  • [3] A Cognitive Memory-Augmented Network for Visual Anomaly Detection
    Tian Wang
    Xing Xu
    Fumin Shen
    Yang Yang
    [J]. IEEE/CAA Journal of Automatica Sinica, 2021, 8 (07) : 1296 - 1307
  • [4] Hyperspectral anomaly detection via memory-augmented autoencoders
    Zhao, Zhe
    Sun, Bangyong
    [J]. CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY, 2023, 8 (04) : 1274 - 1287
  • [5] Comparative learning based stance agreement detection framework for multi-target stance detection
    Liu, Guan-Tong
    Zhang, Yi-Jia
    Wang, Chun-Ling
    Lu, Ming-Yu
    Tang, Huan-Ling
    [J]. ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2024, 133
  • [6] Network Anomaly Detection Using Memory-Augmented Deep Autoencoder
    Min, Byeongjun
    Yoo, Jihoon
    Kim, Sangsoo
    Shin, Dongil
    Shin, Dongkyoo
    [J]. IEEE ACCESS, 2021, 9 : 104695 - 104706
  • [7] Multi-Target Stance Detection Based on GRU-PWV-CNN Network Model
    Li, Wenfa
    Xu, Yilong
    Wang, Gongming
    [J]. JOURNAL OF INTERNET TECHNOLOGY, 2021, 22 (03): : 593 - 603
  • [8] Memory-Augmented Theory of Mind Network
    Dung Nguyen
    Phuoc Nguyen
    Hung Le
    Kien Do
    Venkatesh, Svetha
    Truyen Tran
    [J]. THIRTY-SEVENTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, VOL 37 NO 10, 2023, : 11630 - 11637
  • [9] A Multi-Task Learning Framework for Multi-Target Stance Detection
    Li, Yingjie
    Caragea, Cornelia
    [J]. FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, ACL-IJCNLP 2021, 2021, : 2320 - 2326
  • [10] Memory-augmented appearance-motion network for video anomaly detection
    Wang, Le
    Tian, Junwen
    Zhou, Sanping
    Shi, Haoyue
    Hua, Gang
    [J]. PATTERN RECOGNITION, 2023, 138