提出AF-MAT模型，提升情感分析中长距离依赖与局部细节的捕捉能力。
AF-MAT: Aspect-aware Flip-and-Fuse xLSTM for Aspect-based Sentiment Analysis
- 引入面向观点的门控机制，动态聚焦目标方面相关词语。
- 设计翻转融合块，分阶段建模短距反向与长距正向依赖。
- 轻量级多头跨特征融合，自适应整合不同层级语义表示。
基于观点的情感分析（ABSA）是自然语言处理中的关键任务，旨在从文本（如产品评论）中提取细粒度意见和情感。现有方法常在效率与性能间权衡：传统LSTM或RNN难以捕捉长距离依赖，基于Transformer的方法计算开销大，而基于Mamba的方法依赖CUDA且弱化局部建模。近期提出的扩展长短期记忆（xLSTM）通过指数门控和增强记忆变体（sLSTM用于局部依赖，mLSTM用于可扩展并行记忆）提供了新路径。然而其在ABSA中的应用尚未探索。为此，本文提出面向观点的翻转-融合xLSTM（AF-MAT），利用xLSTM优势。AF-MAT包含面向观点的矩阵LSTM（AA-mLSTM）机制，引入专用观点门，使模型在更新记忆时选择性强调与目标观点语义相关的词元。为建模多尺度上下文，引入FlipMix模块，依次使用部分翻转的一维卷积（pf-Conv1D）捕捉反向短程依赖，再通过全翻转mLSTM（ff-mLSTM）实现全序列反转下的长程依赖建模。此外，提出轻量级多头跨特征融合MC2F，基于mLSTM门控，动态融合AA-mLSTM输出（查询与键）与FlipMix输出（值），实现自适应表征集成。在三个基准数据集上的实验表明，AF-MAT优于当前最优基线，在ABSA任务中取得更高准确率。
原文摘要 · Abstract (English)
Aspect-based Sentiment Analysis (ABSA) is a crucial NLP task that extracts fine-grained opinions and sentiments from text, such as product reviews and customer feedback. Existing methods often trade off efficiency for performance: traditional LSTM or RNN models struggle to capture long-range dependencies, transformer-based methods are computationally costly, and Mamba-based approaches rely on CUDA and weaken local dependency modeling. The recently proposed Extended Long Short-Term Memory (xLSTM) model offers a promising alternative by effectively capturing long-range dependencies through exponential gating and enhanced memory variants, sLSTM for modeling local dependencies, and mLSTM for scalable, parallelizable memory. However, xLSTM's application in ABSA remains unexplored. To address this, we introduce Aspect-aware Flip-and-Fuse xLSTM (AF-MAT), a framework that leverages xLSTM's strengths. AF-MAT features an Aspect-aware matrix LSTM (AA-mLSTM) mechanism that introduces a dedicated aspect gate, enabling the model to selectively emphasize tokens semantically relevant to the target aspect during memory updates. To model multi-scale context, we incorporate a FlipMix block that sequentially applies a partially flipped Conv1D (pf-Conv1D) to capture short-range dependencies in reverse order, followed by a fully flipped mLSTM (ff-mLSTM) to model long-range dependencies via full sequence reversal. Additionally, we propose MC2F, a lightweight Multihead Cross-Feature Fusion based on mLSTM gating, which dynamically fuses AA-mLSTM outputs (queries and keys) with FlipMix outputs (values) for adaptive representation integration. Experiments on three benchmark datasets demonstrate that AF-MAT outperforms state-of-the-art baselines, achieving higher accuracy in ABSA tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。