基于交互注意力机制的多模态情感分析模型  

Multi-modal sentiment analysis model based on interactive attention mechanism

作　　者：周柏男 李旭 范丰龙[1] 姚春龙[1] ZHOU Bainan;LI Xu;FAN Fenglong;YAO Chunlong(School of Information Science and Engineering,Dalian Polytechnic University,Dalian 116034,China;Engineering Training Center,Dalian Polytechnic University,Dalian 116034,China)

机构地区：[1]大连工业大学信息科学与工程学院,辽宁大连116034 [2]大连工业大学工程训练中心,辽宁大连116034

出　　处：《大连工业大学学报》2023年第5期378-384,共7页Journal of Dalian Polytechnic University

基　　金：辽宁省教育厅青年科技人才“育苗”项目(J2020113);辽宁省教育厅科学研究项目(LJKZ0537).

摘　　要：提出一种基于交互注意力机制的多任务模型,利用模态间注意力机制、单模态自注意力机制将多模态情感分析和单模态情感分析联合训练,实现充分利用模态间以及各个任务之间信息共享、相互补充、减少噪声以提高整体识别性能的目的。实验证明所提出模型在多模态情感分析公共数据集MOSI和MOSEI上有良好表现。A multi-task model based on interactive attention mechanism is proposed.The intermodal attention mechanism and single-modal self-attention mechanism are used to jointly train multi-modal sentiment analysis and single-modal sentiment analysis,which makes full use of information sharing between modes and tasks,complement each other,and reduce noise to improve the overall recognition performance.Experimental results show that the proposed model performs well on the public datasets MOSI and MOSEI of multi-modal sentiment analysis.

关 键 词：多模态情感分析 注意力机制 多任务联合训练 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]