基于元优化特征解耦的多模态跨域情感分析算法
A Multimodal Cross-Domain Sentiment Analysis Algorithm Based on Feature Disentanglement Meta-Optimization
-
摘要: 多模态情感分析旨在利用多模态点评等数据识别用户情感倾向。为实现存在域偏移的跨域应用，常用无监督领域自适应方法。然而，该类方法着重于领域不变特征提取，忽略了目标领域特定特征的重要作用。为此，本文提出基于元优化的领域不变及领域特定特征解耦网络。首先，通过嵌入情感适配器对预训练大模型微调，建立图文融合情感特征编码器。进而，构建基于因子分解的特征解耦模块，分别利用领域对抗及领域分类、协同独立性约束，实现知识可传递的领域不变特征编码的同时，提取领域特定特征以增强目标域情感分类性能。为保证特征解耦与情感分类的总体优化方向一致性，提出基于元学习的元优化训练策略，实现情感分析网络的协同优化。基于MVSA和Yelp数据集构建的双向情感迁移任务的对比实验表明，较之其他先进的图文情感迁移算法，本文算法于双向情感迁移任务的精确率、召回率和F1分数三项评价指标均取得了优异的性能。Abstract: Multimodal sentiment analysis aims to utilize the multimodal customer comments and other data to identify users' sentimental tendencies. To realize cross-domain application with the domain bias, commonly used solutions are unsupervised domain adaptation methods. Nevertheless, this type of solutions focuses on the extraction of domain-invariant features, and it neglects the significance of domain-specific features at the target domain. Thus, this paper proposes a meta-optimization based domain-invariant and domain-specific feature disentanglement network. First, by embedding adapters into the pre-trained large model with fine-tuning fitting, the image-text fused sentiment feature encoder is accordingly constructed. Then, a feature disentanglement module is built on the basis of the factorization operation. Constraint by the domain adversary and the domain classification, together with the independence constraint, the knowledge-transferable domain-invariant feature embedding is realized. Meanwhile, the domain-specific features are extracted to enhance sentiment classification at the target domain. To ensure the consistency of the overall optimization tendency for feature disentanglement and sentiment classification, a meta-learning-based meta-optimization training strategy is put forward to synergistically optimize the sentiment analysis network. Comparative experiments on bidirectional sentiment transfer tasks constructed by MVSA and Yelp datasets demonstrate that compared to other advanced image-text sentiment transfer algorithms, the proposed algorithm achieves superior performance on bidirectional sentiment transfer tasks in terms of three consensus metrics: Precision, Recall and F1 score.
-
计量
- 文章访问数: 5
- HTML全文浏览量: 0
- PDF下载量: 1
下载:
