Multimodal Sentiment Analysis (MSA) leverages heterogeneous modalities, such as language, vision, and audio, to enhance the understanding of human sentiment. While existing models often focus on extracting shared information across modalities or directly fusing heterogeneous modalities, such approaches can introduce redundancy and conflicts due to equal treatment of all modalities and the mutual transfer of information between modality pairs. To address these issues, we propose a Disentangled-Language-Focused (DLF) multimodal representation learning framework, which incorporates a feature disentanglement module to separate modality-shared and modality-specific information. To further reduce redundancy and enhance language-targeted features, four geometric measures are introduced to refine the disentanglement process. A Language-Focused Attractor (LFA) is further developed to strengthen language representation by leveraging complementary modality-specific information through a language-guided cross-attention mechanism. The framework also employs hierarchical predictions to improve overall accuracy. Extensive experiments on two popular MSA datasets, CMU-MOSI and CMU-MOSEI, demonstrate the significant performance gains achieved by the proposed DLF framework. Comprehensive ablation studies further validate the effectiveness of the feature disentanglement module, language-focused attractor, and hierarchical predictions. Our code is available at https://github.com/pwang322/DLF.

翻译：多模态情感分析（MSA）利用语言、视觉和音频等异构模态来增强对人类情感的理解。现有模型通常侧重于提取跨模态的共享信息或直接融合异构模态，但由于对所有模态的平等处理以及模态对之间的信息相互传递，此类方法可能引入冗余和冲突。为解决这些问题，我们提出了一种面向解耦语言（DLF）的多模态表示学习框架，该框架包含一个特征解耦模块，用于分离模态共享信息和模态特定信息。为进一步减少冗余并增强面向语言的特征，我们引入了四种几何度量来优化解耦过程。我们还进一步开发了一种语言聚焦吸引器（LFA），通过语言引导的交叉注意力机制利用互补的模态特定信息来强化语言表示。该框架还采用分层预测来提高整体准确性。在两个流行的MSA数据集CMU-MOSI和CMU-MOSEI上进行的大量实验表明，所提出的DLF框架实现了显著的性能提升。全面的消融研究进一步验证了特征解耦模块、语言聚焦吸引器和分层预测的有效性。我们的代码可在 https://github.com/pwang322/DLF 获取。