北京大学学报自然科学版 ›› 2019, Vol. 55 ›› Issue (1): 29-36.DOI: 10.13209/j.0479-8023.2018.064

上一篇    下一篇

基于对抗学习的讽刺识别研究

张庆林, 杜嘉晨, 徐睿峰   

  1. 哈尔滨工业大学(深圳)计算机科学与技术学院, 深圳 518055
  • 收稿日期:2018-06-30 修回日期:2018-08-18 出版日期:2019-01-20 发布日期:2019-01-20
  • 通讯作者: 徐睿峰, E-mail: xuruifeng(at)hit.edu.cn
  • 基金资助:
    国家自然科学基金(U1636103, 61632011)、深圳市基础研究计划(20170307150024907)和深圳市技术攻关项目(JSGG20170817140856618)资助

Sarcasm Detection Based on Adversarial Learning

ZHANG Qinglin, DU Jiachen, XU Ruifeng   

  1. School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen 518055
  • Received:2018-06-30 Revised:2018-08-18 Online:2019-01-20 Published:2019-01-20
  • Contact: XU Ruifeng, E-mail: xuruifeng(at)hit.edu.cn

摘要:

为了避免现有讽刺识别方法的性能会受训练数据缺乏的影响, 在使用有限标注数据训练的注意力卷积神经网络基础上, 提出一种对抗学习框架, 该框架包含两种互补的对抗学习方法。首先, 提出一种基于对抗样本的学习方法, 应用对抗生成的样本参与模型训练, 以期提高分类器的鲁棒性和泛化能力。进而, 研究基于领域迁移的对抗学习方法, 以期利用跨领域讽刺表达数据, 改善模型在目标领域上的识别性能。在3个讽刺数据集上的实验结果表明, 两种对抗学习方法都能提高讽刺识别的性能, 其中基于领域迁移方法的性能提升更显著; 同时结合两种对抗学习方法能够进一步提高讽刺识别性能。

关键词: 讽刺识别, 对抗学习, 注意力机制, 卷积神经网络, 对抗样本

Abstract:

Existing sarcasm detection approaches suffer from lack of sufficient training data. To address this problem, the authors propose an adversarial learning framework built on convolutional neural network (CNN) and attention mechanism, which is trained from limited amounts of labeled data. Two complementary adversarial learning approaches are investigated. First, by training with generated adversarial examples, the authors attempt to enhance the robustness and generalization ability of the classifier. Then, a domain transfer based adversarial learning approach is proposed to leverage cross-domain sarcasm data for improving the performance of sarcasm detection in the target domain. Experimental results on three sarcasm datasets show that both adversarial learning approaches proposed improve the performance of sarcasm detection, but the domain transfer based approach achieves higher performance. Combining the two proposed approaches further improves the performance of sarcasm detection.

Key words: sarcasm detection, adversarial learning, attention mechanism, convolutional neural network, adversarial examples