Enhancing Long-Range Dependency with State Space Model and Kolmogorov-Arnold Networks for Aspect-Based Sentiment Analysis
This work addresses a specific bottleneck in ABSA for natural language processing applications, offering an incremental improvement over existing methods.
The paper tackles the problem of capturing long-range dependencies between aspect and opinion words in Aspect-Based Sentiment Analysis (ABSA), where attention mechanisms struggle due to quadratic complexity, by proposing MambaForGCN, which combines syntax-based Graph Convolutional Networks, Mamba-Transformer modules, and Kolmogorov-Arnold Networks gated fusion, achieving state-of-the-art results on three benchmark datasets.
Aspect-based Sentiment Analysis (ABSA) evaluates sentiments toward specific aspects of entities within the text. However, attention mechanisms and neural network models struggle with syntactic constraints. The quadratic complexity of attention mechanisms also limits their adoption for capturing long-range dependencies between aspect and opinion words in ABSA. This complexity can lead to the misinterpretation of irrelevant contextual words, restricting their effectiveness to short-range dependencies. To address the above problem, we present a novel approach to enhance long-range dependencies between aspect and opinion words in ABSA (MambaForGCN). This approach incorporates syntax-based Graph Convolutional Network (SynGCN) and MambaFormer (Mamba-Transformer) modules to encode input with dependency relations and semantic information. The Multihead Attention (MHA) and Selective State Space model (Mamba) blocks in the MambaFormer module serve as channels to enhance the model with short and long-range dependencies between aspect and opinion words. We also introduce the Kolmogorov-Arnold Networks (KANs) gated fusion, an adaptive feature representation system that integrates SynGCN and MambaFormer and captures non-linear, complex dependencies. Experimental results on three benchmark datasets demonstrate MambaForGCN's effectiveness, outperforming state-of-the-art (SOTA) baseline models.