Transformer及门控注意力模型在特定对象立场检测中的应用
作者:
基金项目:

中国科学院战略性先导科技专项(C 类) (XDC02060100)


Transformer and Gated Attention Model on Target-Specific Stance Detection
Author:
  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [15]
  • |
  • 相似文献
  • |
  • 引证文献
  • | |
  • 文章评论
    摘要:

    立场检测旨在通过意见持有者的表达来判断其是支持还是反对给定对象. 准确地检测立场不仅需要对表达内容进行信息提取, 而且还需要针对特定的对象进行立场匹配. 本文将Transformer结构与门控注意力模型应用在特定对象立场检测中. 该模型可以有效利用推文中独特的标签短语信息, 同时结合门控注意力机制形成推文与对象的匹配信息, 从而更好地判断该推文对该对象的真实立场. 此外, 该方法将情感分类作为辅助任务, 可以更充分地将情感信息纳入立场判别当中, 提高模型的表现. 实验结果表明, 该模型在 SemEval-2016数据集上表现优于最新的深度学习方法.

    Abstract:

    Stance detection tells whether the expressions of opinion holders are in favor of or against the given objects. To accurately detect stance, the information of the expressed contents must be extracted, alongside a stance match for specific objects. In this study, the Transformer structure and gating attention is applied to specific object stance detection. By effectively utilizing the tag phrase information of the posts and the matching information between posts and objects, which are a result of gating attention mechanism, it delivers a better judgment over the post’s authentic stance regarding the object. Moreover, this approach takes emotional classification as an auxiliary task to fully include emotional information into stance detection for better performance. Experimental results show that the model is superior to the latest deep learning method on the SemEval-2016 dataset.

    参考文献
    [1] Sennrich R, Haddow B, Birch A. Neural machine translation of rare words with subword units. arXiv: 1508.07909, 2015.
    [2] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need. Proceedings of Advances in Neural Information Processing Systems. Long Beach, CA, USA. 2017. 5998-6008.
    [3] Devlin J, Chang MW, Lee K, et al. BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv: 1810.04805, 2018.
    [4] Mohammad S, Kiritchenko S, Sobhani P, et al. Semeval-2016 task 6: Detecting stance in tweets. Proceedings of the 10th International Workshop on Semantic Evaluation. San Diego, CA, USA. 2016. 31-41.
    [5] Vijayaraghavan P, Sysoev I, Vosoughi S, et al. Deepstance at semeval-2016 task 6: Detecting stance in tweets using character and word-level cnns. arXiv: 1606.05694, 2016.
    [6] Wei W, Zhang X, Liu XQ, et al. Pkudblab at semeval-2016 task 6: A specific convolutional neural network system for effective stance detection. Proceedings of the 10th International Workshop on Semantic Evaluation. San Diego, CA, USA. 2016. 384-388.
    [7] Zarrella G, Marsh A. Mitre at SemEval-2016 task 6: Transfer learning for stance detection. arXiv: 1606.03784, 2016.
    [8] Du JC, Xu RF, He YL, et al. Stance classification with target-specific neural attention networks. Proceedings of the 26th International Joint Conference on Artificial Intelligence. Sydney, Australia. 2017. 3988-3994.
    [9] Zhou YW, Cristea AI, Shi L. Connecting targets to tweets: Semantic attention-based model for target-specific stance detection. Proceedings of the 18th International Conference on Web Information Systems Engineering. Moscow, Russia. 2017. 18-32.
    [10] Sun QY, Wang ZQ, Zhu QM, et al. Stance detection with hierarchical attention network. Proceedings of the 27th International Conference on Computational Linguistics. Santa Fe, NM, USA. 2018. 2399-2409.
    [11] Sobhani P, Mohammad S, Kiritchenko S. Detecting stance in tweets and analyzing its interaction with sentiment. Proceedings of the 5th Joint Conference on Lexical And Computational Semantics. Berlin, Germany. 2016. 159-169.
    [12] Sun QY, Wang ZQ, Li SS, et al. Stance detection via sentiment information and neural network model. Frontiers of Computer Science, 2019, 13(1): 127-138. [doi: 10.1007/s11704-018-7150-9
    [13] Shen DH, Wang GY, Wang WL, et al. Baseline needs more love: On simple word-embedding-based models and associated pooling mechanisms. arXiv: 1805.09843, 2018.
    [14] Tang DY, Qin B, Feng XC, et al. Effective LSTMs for target-dependent sentiment classification. arXiv: 1512.01100, 2015.
    [15] Wei PH, Mao WJ, Zeng D. A target-guided neural memory model for stance detection in Twitter. Proceedings of 2018 International Joint Conference on Neural Networks (IJCNN). Rio de Janeiro, Brazil. 2018. 1-8.
    相似文献
    引证文献
引用本文

何孝霆,董航,杜义华. Transformer及门控注意力模型在特定对象立场检测中的应用.计算机系统应用,2020,29(11):232-236

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2020-01-07
  • 最后修改日期:2020-01-22
  • 在线发布日期: 2020-10-30
文章二维码
您是第11203767位访问者
版权所有:中国科学院软件研究所 京ICP备05046678号-3
地址:北京海淀区中关村南四街4号 中科院软件园区 7号楼305房间,邮政编码:100190
电话:010-62661041 传真: Email:csa (a) iscas.ac.cn
技术支持:北京勤云科技发展有限公司

京公网安备 11040202500063号