用脉冲神经网络实现低功耗方面词提取，性能媲美主流模型。
Efficient Aspect Term Extraction using Spiking Neural Network
- 采用脉冲神经网络与稀疏激活机制，通过事件驱动推理捕捉词序依赖。
- 在四个SemEval数据集上达到与先进DNN相当的准确率，能耗显著降低。
- 适合资源受限场景，如边缘设备部署的轻量级情感分析任务。
方面词提取（ATE）从评论句子中识别方面词，是情感分析的关键子任务。现有方法多使用能耗高的深度神经网络（DNN）进行序列标注，本文提出一种更节能的替代方案——脉冲神经网络（SNN）。SNN利用稀疏激活和事件驱动推理，有效捕捉词语间的时序依赖，适用于ATE任务。所提出的SpikeATE架构采用三值脉冲神经元，并通过伪梯度微调直接训练脉冲信号。在四个基准SemEval数据集上评估显示，SpikeATE性能与当前最优DNN相当，但能耗显著更低。这表明SNN可作为ATE任务中实际且可持续的选择。
原文摘要 · Abstract (English)
Aspect Term Extraction (ATE) identifies aspect terms in review sentences, a key subtask of sentiment analysis. While most existing approaches use energy-intensive deep neural networks (DNNs) for ATE as sequence labeling, this paper proposes a more energy-efficient alternative using Spiking Neural Networks (SNNs). Using sparse activations and event-driven inferences, SNNs capture temporal dependencies between words, making them suitable for ATE. The proposed architecture, SpikeATE, employs ternary spiking neurons and direct spike training fine-tuned with pseudo-gradients. Evaluated on four benchmark SemEval datasets, SpikeATE achieves performance comparable to state-of-the-art DNNs with significantly lower energy consumption. This highlights the use of SNNs as a practical and sustainable choice for ATE 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。