Leveraging Chain-of-Thought to Enhance Stance Detection with Prompt-Tuning

被引:0
|
作者
Ding, Daijun [1 ]
Fu, Xianghua [2 ]
Peng, Xiaojiang [2 ]
Fan, Xiaomao [2 ]
Huang, Hu [3 ]
Zhang, Bowen [2 ]
机构
[1] Shenzhen Univ, Coll Appl Sci, Shenzhen 518052, Peoples R China
[2] Shenzhen Technol Univ, Coll Big Data & Internet, Shenzhen 518118, Peoples R China
[3] Peking Univ, Shenzhen Grad Sch, Shenzhen 518055, Peoples R China
关键词
stance detection; prompt-tuning; chain-of-thought;
D O I
10.3390/math12040568
中图分类号
O1 [数学];
学科分类号
0701 ; 070101 ;
摘要
Investigating public attitudes towards social media is crucial for opinion mining systems to gain valuable insights. Stance detection, which aims to discern the attitude expressed in an opinionated text towards a specific target, is a fundamental task in opinion mining. Conventional approaches mainly focus on sentence-level classification techniques. Recent research has shown that the integration of background knowledge can significantly improve stance detection performance. Despite the significant improvement achieved by knowledge-enhanced methods, applying these techniques in real-world scenarios remains challenging for several reasons. Firstly, existing methods often require the use of complex attention mechanisms to filter out noise and extract relevant background knowledge, which involves significant annotation efforts. Secondly, knowledge fusion mechanisms typically rely on fine-tuning, which can introduce a gap between the pre-training phase of pre-trained language models (PLMs) and the downstream stance detection tasks, leading to the poor prediction accuracy of the PLMs. To address these limitations, we propose a novel prompt-based stance detection method that leverages the knowledge acquired using the chain-of-thought method, which we refer to as PSDCOT. The proposed approach consists of two stages. The first stage is knowledge extraction, where instruction questions are constructed to elicit background knowledge from a VLPLM. The second stage is the multi-prompt learning network (M-PLN) for knowledge fusion, which learns model performance based on the background knowledge and the prompt learning framework. We evaluated the performance of PSDCOT on publicly available benchmark datasets to assess its effectiveness in improving stance detection performance. The results demonstrate that the proposed method achieves state-of-the-art results in in-domain, cross-target, and zero-shot learning settings.
引用
收藏
页数:16
相关论文
共 8 条
  • [1] Knowledge-enhanced Prompt-tuning for Stance Detection
    Huang, Hu
    Zhang, Bowen
    Li, Yangyang
    Zhang, Baoquan
    Sun, Yuxi
    Luo, Chuyao
    Peng, Cheng
    [J]. ACM TRANSACTIONS ON ASIAN AND LOW-RESOURCE LANGUAGE INFORMATION PROCESSING, 2023, 22 (06)
  • [2] SEGP: Stance-Emotion Joint Data Augmentation with Gradual Prompt-Tuning for Stance Detection
    Wang, Junlin
    Zhou, Yan
    Liu, Yaxin
    Zhang, Weibo
    Hu, Songlin
    [J]. COMPUTATIONAL SCIENCE - ICCS 2022, PT III, 2022, 13352 : 577 - 590
  • [3] Distantly Supervised Explainable Stance Detection via Chain-of-Thought Supervision
    Ding, Daijun
    Dai, Genan
    Peng, Cheng
    Peng, Xiaojiang
    Zhang, Bowen
    Huang, Hu
    [J]. MATHEMATICS, 2024, 12 (07)
  • [4] Incorporating target-aware knowledge into prompt-tuning for few-shot stance detection
    Wang, Shaokang
    Sun, Fuhui
    Wang, Xiaoyan
    Pan, Li
    [J]. INFORMATION PROCESSING & MANAGEMENT, 2024, 61 (05)
  • [5] Clickbait Detection via Prompt-Tuning With Titles Only
    Wang, Ye
    Zhu, Yi
    Li, Yun
    Qiang, Jipeng
    Yuan, Yunhao
    Wu, Xindong
    [J]. IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE, 2024,
  • [6] PSCVFinder: A Prompt-Tuning Based Framework for Smart Contract Vulnerability Detection
    Yu, Lei
    Lu, Junyi
    Liu, Xianglong
    Yang, Li
    Zhang, Fengjun
    Ma, Jiajia
    [J]. 2023 IEEE 34TH INTERNATIONAL SYMPOSIUM ON SOFTWARE RELIABILITY ENGINEERING, ISSRE, 2023, : 556 - 567
  • [7] Prompt Engineering for Knowledge Creation: Using Chain-of-Thought to Support Students' Improvable Ideas
    Lee, Alwyn Vwen Yen
    Teo, Chew Lee
    Tan, Seng Chee
    [J]. AI, 2024, 5 (03) : 1446 - 1461
  • [8] Real Estate Insights Unleashing the potential of ChatGPT in property valuation reports: the "Red Book" compliance Chain-of-thought (CoT) prompt engineering
    Cheung, Ka Shing
    [J]. JOURNAL OF PROPERTY INVESTMENT & FINANCE, 2024, 42 (02) : 200 - 206