Unsupervised Opinion Summarization with Content Planning

被引:0
|
作者
Amplayo, Reinald Kim [1 ]
Angelidis, Stefanos [1 ]
Lapata, Mirella [1 ]
机构
[1] Univ Edinburgh, Sch Informat, Inst Language Cognit & Computat, Edinburgh, Midlothian, Scotland
基金
欧洲研究理事会;
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
The recent success of deep learning techniques for abstractive summarization is predicated on the availability of large-scale datasets. When summarizing reviews (e.g., for products or movies), such training data is neither available nor can be easily sourced, motivating the development of methods which rely on synthetic datasets for supervised training. We show that explicitly incorporating content planning in a summarization model not only yields output of higher quality, but also allows the creation of synthetic datasets which are more natural, resembling real world document-summary pairs. Our content plans take the form of aspect and sentiment distributions which we induce from data without access to expensive annotations. Synthetic datasets are created by sampling pseudo-reviews from a Dirichlet distribution parametrized by our content planner, while our model generates summaries based on input reviews and induced content plans. Experimental results on three domains show that our approach outperforms competitive models in generating informative, coherent, and fluent summaries that capture opinion consensus.
引用
收藏
页码:12489 / 12497
页数:9
相关论文
共 50 条
  • [1] Unsupervised Opinion Summarization with Noising and Denoising
    Amplayo, Reinald Kim
    Lapata, Mirella
    58TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2020), 2020, : 1934 - 1945
  • [2] Unsupervised Opinion Summarization Using Approximate Geodesics
    Chowdhury, Somnath Basu Roy
    Monath, Nicholas
    Dubey, Avinava
    Ahmed, Amr
    Chaturvedi, Snigdha
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS - EMNLP 2023, 2023, : 97 - 112
  • [3] Aspect-aware Unsupervised Extractive Opinion Summarization
    Li, Haoyuan
    Chowdhury, Somnath Basu Roy
    Chaturvedi, Snigdha
    FINDINGS OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2023), 2023, : 12662 - 12678
  • [4] Unsupervised Extractive Opinion Summarization Using Sparse Coding
    Chowdhury, Somnath Basu Roy
    Zhao, Chao
    Chaturvedi, Snigdha
    PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022), VOL 1: (LONG PAPERS), 2022, : 1209 - 1225
  • [5] ConsistSum: Unsupervised Opinion Summarization with the Consistency of Aspect, Sentiment and Semantic
    Ke, Wenjun
    Gao, Jinhua
    Shen, Huawei
    Cheng, Xueqi
    WSDM'22: PROCEEDINGS OF THE FIFTEENTH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING, 2022, : 467 - 475
  • [6] AsU-OSum: Aspect-augmented unsupervised opinion summarization
    Zhang, Mengli
    Zhou, Gang
    Huang, Ningbo
    He, Peng
    Yu, Wanting
    Liu, Wenfen
    INFORMATION PROCESSING & MANAGEMENT, 2023, 60 (01)
  • [7] Simple Yet Effective Synthetic Dataset Construction for Unsupervised Opinion Summarization
    Shen, Ming
    Ma, Jie
    Wang, Shuai
    Vyas, Yogarshi
    Dixit, Kalpit
    Ballesteros, Miguel
    Benajiba, Yassine
    17TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, EACL 2023, 2023, : 1898 - 1911
  • [8] An unsupervised opinion summarization model fused joint attention and dictionary learning
    Xiong, Yu
    Yan, Minghe
    Hu, Xiang
    Ren, Chaohui
    Tian, Hang
    JOURNAL OF SUPERCOMPUTING, 2023, 79 (16): : 17759 - 17783
  • [9] An unsupervised opinion summarization model fused joint attention and dictionary learning
    Yu Xiong
    Minghe Yan
    Xiang Hu
    Chaohui Ren
    Hang Tian
    The Journal of Supercomputing, 2023, 79 : 17759 - 17783
  • [10] Unsupervised extractive opinion summarization based on text simplification and sentiment guidance
    Wang, Rui
    Lan, Tian
    Wu, Zufeng
    Liu, Leyuan
    EXPERT SYSTEMS WITH APPLICATIONS, 2025, 272