一种量子概率启发的对话讽刺识别网络模型

张亚洲; 俞洋; 朱少林; 陈锐; 戎璐; 梁辉

doi:10.12263/DZXB.20211075

您当前的位置：

首页 >

文章列表页 >

一种量子概率启发的对话讽刺识别网络模型

学术论文 | 更新时间：2025-12-08

- 一种量子概率启发的对话讽刺识别网络模型
- A Quantum Probability Inspired Network for Dialogue Sarcasm Recognition
- 电子学报 2022年50卷第8期页码：1885-1893
- 作者机构：
  
  郑州轻工业大学软件学院，河南郑州 450002
- 作者简介：
  
  [ "张亚洲男，1990年11月出生于河南省安阳市.现为郑州轻工业大学软件学院讲师、硕士生导师.主要研究方向为多模态情感分析.E-mail：yzzhang@zzuli.edu.cn" ]
  [ "俞洋男，1998年8月出生于河南省信阳市 . 现为郑州轻工业大学软件学院硕士生 . 主要研究方向为多模态情感分析. E-mail：yuyang19980818@outlook.com" ]
  [ "朱少林男，1989年11月出生于河南省新乡市.现为郑州轻工业大学软件学院讲师.主要研究方向为多模态机器翻译.E-mail： zhushaolin003@163.com" ]
  [ "陈锐男，1979年12月出生，现为郑州轻工业大学软件学院讲师.主要研究方向为社交网络分析、个性化推荐.E-mail： ruichen@zzuli.edu.cn" ]
  [ "戎璐女，1995年1月出生于山西省忻州市.现为郑州轻工业大学助理讲师.主要研究方向为自然语言理解.E-mail： lurong2013@outlook.com" ]
  [ "梁辉男，1977年1月生于河南省平顶山市.现为郑州轻工业大学软件学院教授.主要研究方向为数字媒体、虚拟现实、计算机动画技术." ]
- 基金信息：
  
  国家自然科学基金(62006212);河南省重点研发与推广专项（科技攻关）(212102210418)
- DOI：10.12263/DZXB.20211075
  中图分类号： TP391
- 收稿：2021-08-11，
  
  修回：2022-04-11，
  
  纸质出版：2022-08-25
- 稿件说明：
移动端阅览
张亚洲,俞洋,朱少林等.一种量子概率启发的对话讽刺识别网络模型[J].电子学报,2022,50(08):1885-1893.

ZHANG Ya-zhou,YU Yang,ZHU Shao-lin,et al.A Quantum Probability Inspired Network for Dialogue Sarcasm Recognition[J].ACTA ELECTRONICA SINICA,2022,50(08):1885-1893.
张亚洲,俞洋,朱少林等.一种量子概率启发的对话讽刺识别网络模型[J].电子学报,2022,50(08):1885-1893. DOI： 10.12263/DZXB.20211075.

ZHANG Ya-zhou,YU Yang,ZHU Shao-lin,et al.A Quantum Probability Inspired Network for Dialogue Sarcasm Recognition[J].ACTA ELECTRONICA SINICA,2022,50(08):1885-1893. DOI： 10.12263/DZXB.20211075.

摘要

对话讽刺识别已经成为人工智能领域中一项极具挑战性的课题，其目的是辨别互动对话中晦涩难懂的诸如讽刺、轻蔑、嘲笑等隐喻性情感.从语言哲学分析，目前的对话讽刺识别方法难以衡量人类语言在讽刺表达与理解方面固有的不确定性.鉴于量子概率在建模不确定性方面的优势，本文探索量子概率在讽刺识别领域的潜力并提出一种量子概率启发式网络.该网络主要包含复值嵌入层、量子复合层、量子测量层以及全连接层.本文将互动对话中每句话语视作是一组单词的类量子叠加，表征为复数向量.相邻话语之间的上下文交互被建模为量子系统与其周围环境的复合，表示为密度矩阵.本文对每句话语进行量子测量，提取讽刺特征，并将讽刺特征输入到全连接层预测得到讽刺识别结果.本文在两个基准数据集上进行实验，结果表明本文提出的模型优于先进讽刺识别模型，讽刺识别准确率分别提升5.2%与2.38%.

Abstract

Dialogue sarcasm recognition has been a challenging artificial intelligence(AI) research topic

aiming to discover elusive ironic

contemptuous and metaphoric information implied in daily dialogue. From the perspective of emotional logic

most existing works are insufficient to measure the intrinsic uncertainty in emotional expression and understanding. In view of the advantages of quantum probability(QP) in modeling the uncertainty

this paper explores the potential of QP in dialogue sarcasm recognition and proposes a quantum probability inspired network(QPIN). Specially

QPIN consists of a complex-valued embedding layer

a quantum composition layer

a quantum measurement layer and a dense layer. Each utterance is treated as a quantum superposition-like of a set of basis words

using a complex-valued representation. The contextual interaction between adjacent utterances is described as the composition system between a quantum system and its surrounding environment

which is represented by the density matrix. A quantum measurement is performed on the density matrix of each utterance to extract sarcastic features

and thus feeds these features to a dense layer to yield the probabilistic outcomes. Extensive experiments are conducted on two benchmark datasets

and the results show that our model outperforms the state-of-the-art baselines

with accuracy scores enhanced by 5.2% and 2.38%

respectively.

关键词

Keywords

references

ZHANG Y , LI X , RONG L , TIWARI P . Multi-task learning for jointly detecting depression and emotion [C]// 2021 IEEE International Conference on Bioinformatics and Biomedicine . Houston, Texas, USA : IEEE , 2021 : 3142 - 3149 .

张仰森 , 周炜翔 , 张禹尧 , 吴云芳 . 一种基于情感计算与层次化多头注意力机制的负面新闻识别方法 [J]. 电子学报 , 2020 , 48 ( 9 ): 1720 - 1728 .

ZHANG Yang-sen , ZHOU Wei-xiang , ZHANG Yu-yao , WU Yun-fang . A negative news recognition method based on emotional computing and hierarchical multi-head attention mechanism [J]. Acta Electronica Sinica , 2020 , 48 ( 9 ): 1720 - 1728 . (in Chinese)

康世泽 , 马宏 , 黄瑞阳 . 一种基于 Opinosis 图和马尔科夫随机游走模型的多文本情感摘要框架 [J]. 电子学报 , 2017 , 45 ( 12 ): 3005 - 3011 .

KANG Shi-ze , MA Hong , HUANG Rui-yang . An Opinosis and MRW based sentiment summarization framework [J]. Acta Electronica Sinica , 2017 , 45 ( 12 ): 3005 - 3011 . (in Chinese)

ZHANG Y , SONG D , LI X , ZHANG P , et al . A quantum-like multimodal network framework for modeling interaction dynamics in multiparty conversational sentiment analysis [J]. Information Fusion , 2020 , 62 ( 1 ): 14 - 31 .

ZHANG Y , TIWARI P , SONG D , et al . Learning interaction dynamics with an interactive LSTM for conversational sentiment analysis [J]. Neural Networks , 2021 , 133 : 40 - 56 .

HUME D . A Treatise of Human Nature [M]. Chicago, USA : Courier Corporation , 2003 .

谭光辉 . 情感分析的几条基本规律 [J]. 内蒙古社会科学(汉文版) , 2018 , 39 ( 1 ): 8 - 14 .

TAN Guang-hui . Basic rules of sentiment analysis [J]. Inner Mongolia Social Sciences , 2018 , 39 ( 1 ): 8 - 14 . (in Chinese)

TVERSKY A , KAHNEMAN D . Extensional versus intuitive reasoning: The conjunction fallacy in probability judgment [J]. Psychological Review , 1983 , 90 ( 4 ): 293 - 315 .

WANG B , ZHANG P , LI J , et al . Exploration of quantum interference in document relevance judgement discrepancy [J]. Entropy , 2016 , 18 ( 4 ): 144 - 150 .

ZHANG Y , SONG D , ZHANG P , et al . A quantum-inspired sentiment representation model for twitter sentiment analysis [J]. Applied Intelligence , 2019 , 49 ( 8 ): 3093 - 3108 .

WANG B , LI Q , MELUCCI M , SONG D . Semantic Hilbert space for text representation learning [C]// Proceedings of the World Wide Web conference . San Francisco, USA : WWW, 2019: 3293-3299 WWW,2019:3293-3299 .

ZHANG Y , SONG D , ZHANG P , et al . A quantum-inspired multimodal sentiment analysis framework [J]. Theoretical Computer Science , 2018 , 752 : 21 - 40 .

LIU Y , ZHANG Y , LI Q , et al . What does your smile mean? jointly detecting multi-modal sarcasm and sentiment using quantum probability [C]// Findings of the Association for Computational Linguistics: EMNLP . Virtual Conference : ACL , 2021 : 871 - 880 .

WANG P , HOU Y , LI Z , ZHANG Y . QIRM: A quantum interactive retrieval model for session search [J]. Neurocomputing , 2021 , 451 : 57 - 66 .

OCHS W . Gleason Measures and Quantum Comparative Probability [M]. Quantum Probability and Applications II . Heidelberg, Germany : Springer , 1985 : 388 - 396 .

CASTRO S , HAZARIKA D , PEREZ-ROSAS V , et al . Towards multimodal sarcasm detection (an obviously perfect paper) [C]// Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics . Florence, Italy : ACL , 2020 : 4619 - 4629 .

GHOSH D , VAJPAYEE A , MURESAN S . A report on the 2020 sarcasm detection shared task [C]// Proceedings of the Second Workshop on Figurative Language Processing . Saarbrücken, Germany : ACL , 2020 : 1 - 11 .

KIM Y . Convolutional neural networks for sentence classification [C]// Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) . Doha, Qatar : ACL , 2014 : 1746 - 1755 .

KUMAR A , NARAPAREDDY VT , SRIKANTH VA , et al . Sarcasm detection using multi-head attention based bidirectional LSTM [J]. IEEE Access , 2020 , 8 ( 1 ): 6388 - 6397 .

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于显著图的电磁信号对抗样本生成方法

面向时序异常检测的可变视距多向扫描方法

基于稀疏平滑自蒸馏的差分隐私深度学习方法

基于非一般类算子融合方法及硬件架构设计