A Unified Generative Framework for Aspect-Based Sentiment Analysis

被引:0
|
作者
Yan, Hang [1 ,2 ]
Dai, Junqi [1 ,2 ]
Ji, Tuo [1 ,2 ]
Qiu, Xipeng [1 ,2 ,3 ]
Zhang, Zheng [4 ]
机构
[1] Fudan Univ, Shanghai Key Lab Intelligent Informat Proc, Shanghai, Peoples R China
[2] Fudan Univ, Sch Comp Sci, Shanghai, Peoples R China
[3] Pazhou Lab, Guangzhou, Peoples R China
[4] NYU, New York, NY 10003 USA
基金
中国国家自然科学基金;
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
Aspect-based Sentiment Analysis (ABSA) aims to identify the aspect terms, their corresponding sentiment polarities, and the opinion terms. There exist seven subtasks in ABSA. Most studies only focus on the subsets of these subtasks, which leads to various complicated ABSA models while hard to solve these subtasks in a unified framework. In this paper, we redefine every subtask target as a sequence mixed by pointer indexes and sentiment class indexes, which converts all ABSA subtasks into a unified generative formulation. Based on the unified formulation, we exploit the pre-training sequence-to-sequence model BART to solve all ABSA subtasks in an endto-end framework. Extensive experiments on four ABSA datasets for seven subtasks demonstrate that our framework achieves substantial performance gain and provides a real unified end-to-end solution for the whole ABSA subtasks, which could benefit multiple tasks(1).
引用
收藏
页码:2416 / 2429
页数:14
相关论文
共 50 条
  • [21] Data augmentation for aspect-based sentiment analysis
    Guangmin Li
    Hui Wang
    Yi Ding
    Kangan Zhou
    Xiaowei Yan
    International Journal of Machine Learning and Cybernetics, 2023, 14 : 125 - 133
  • [22] Target-Aspect-Sentiment Joint Detection for Aspect-Based Sentiment Analysis
    Wan, Hai
    Yang, Yufei
    Du, Jianfeng
    Liu, Yanan
    Qi, Kunxun
    Pan, Jeff Z.
    THIRTY-FOURTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THE THIRTY-SECOND INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE AND THE TENTH AAAI SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2020, 34 : 9122 - 9129
  • [23] Aspect-based sentiment analysis of mobile reviews
    Gupta, Vedika
    Singh, Vivek Kumar
    Mukhija, Pankaj
    Ghose, Udayan
    JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2019, 36 (05) : 4721 - 4730
  • [24] A Survey on Multimodal Aspect-Based Sentiment Analysis
    Zhao, Hua
    Yang, Manyu
    Bai, Xueyang
    Liu, Han
    IEEE ACCESS, 2024, 12 : 12039 - 12052
  • [25] Aspect-Based Sentiment Analysis Approach with CNN
    Mulyo, Budi M.
    Widyantoro, Dwi H.
    2018 5TH INTERNATIONAL CONFERENCE ON ELECTRICAL ENGINEERING, COMPUTER SCIENCE AND INFORMATICS (EECSI 2018), 2018, : 142 - 147
  • [26] A corpus for aspect-based sentiment analysis in Vietnamese
    Nguyen, Minh-Hao
    Nguyen, Tri Minh
    Thin, Dang Van
    Nguyen, Ngan Luu-Thuy
    PROCEEDINGS OF 2019 11TH INTERNATIONAL CONFERENCE ON KNOWLEDGE AND SYSTEMS ENGINEERING (KSE 2019), 2019, : 317 - 321
  • [27] Aspect-Based Sentiment Analysis for User Reviews
    Du, Jinyang
    Zhang, Yin
    Ma, Xiao
    Wen, Haoyu
    Fortino, Giancarlo
    COGNITIVE COMPUTATION, 2021, 13 (05) : 1114 - 1127
  • [28] DRGCN Multitasking for Aspect-Based Sentiment Analysis
    Du, Mengyang
    Wang, Hongbin
    Journal of Advanced Computational Intelligence and Intelligent Informatics, 2025, 29 (02) : 268 - 276
  • [29] An Adaptive Hybrid Framework for Cross-domain Aspect-based Sentiment Analysis
    Zhou, Yan
    Zhu, Fuqing
    Song, Pu
    Han, Jizhong
    Gu, Tao
    Hul, Songlin
    THIRTY-FIFTH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE, THIRTY-THIRD CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE AND THE ELEVENTH SYMPOSIUM ON EDUCATIONAL ADVANCES IN ARTIFICIAL INTELLIGENCE, 2021, 35 : 14630 - 14637
  • [30] A hierarchical and parallel framework for End-to-End Aspect-based Sentiment Analysis
    Xiao, Ding
    Ren, Feiyang
    Pang, Xiaoxuan
    Cai, Ming
    Wang, Qianyu
    He, Ming
    Peng, Jiawei
    Fu, Hao
    NEUROCOMPUTING, 2021, 465 : 549 - 560