模式
计算机科学
代表(政治)
模态(人机交互)
人工智能
情态动词
情绪分析
光学(聚焦)
自然语言处理
机器学习
多模式学习
特征学习
语义学(计算机科学)
社会学
化学
高分子化学
物理
程序设计语言
法学
光学
政治
社会科学
政治学
作者
Zhibang Quan,Tao Sun,Mengli Su,Jishu Wei,Xiang Zhang,Shenjie Zhong
出处
期刊:Conference proceedings
[Institute of Electrical and Electronics Engineers]
日期:2022-10-09
卷期号:: 3086-3091
被引量:10
标识
DOI:10.1109/smc53654.2022.9945514
摘要
Multimodal sentiment analysis is an active subfield of natural language processing. It aims to extract and integrate semantic information gathered from multiple modalities to identify the sentiments expressed by users. Indeed, the complementary and heterogeneous information between modalities influences the prediction results. Recent research proposals employ a single neural network to obtain mutually independent representations of all modalities. However, a problem that may limit previous work from reaching a higher level is that this does not consider the modal heterogeneity problem between different modalities. This, in turn, may lead to the presence of additional noise in the representations before modal fusion. For this reason, we propose a new framework, MICS, which adopts a suitable strategy for each modality and provides a better representation for fusion. Also, we design a multimodal comparative learning interaction module for the fusion phase, which plays a crucial role in the information interaction between modalities. Our extensive experiments on two publicly available and popular benchmarks, MOSI and MOSEI, show that MICS can better focus on the characteristics of different modal data and has significant advantages over previous complex baselines.
科研通智能强力驱动
Strongly Powered by AbleSci AI