Efficient Aspect Term Extraction using Spiking Neural Network

2026-01-10

arXiv.org

AI Summary

This work addresses the high energy consumption of conventional deep neural networks in aspect term extraction by introducing spiking neural networks (SNNs) to this task for the first time. The authors propose a sequence labeling model based on ternary spiking neurons and an event-driven mechanism, which captures inter-word temporal dependencies through sparse activation. By integrating direct spike-based training with pseudo-gradient optimization, the model achieves performance comparable to state-of-the-art deep learning approaches on four SemEval benchmark datasets while significantly reducing energy consumption. These results demonstrate the efficiency and feasibility of SNNs for natural language processing tasks.

Technology Category

Cognitive Modeling & Cognitive Systems: Neural Spike CodingNatural Language Processing: Sentence-level Semantics, Textual Inference, etc.Machine Learning: Deep Neural Architectures and Foundation Models

Application Category

Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphsSearch and Retrieval-Augmented AI: Large language models for searchSemantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

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.

Problem

• Aspect Term Extraction
• Energy Efficiency
• Spiking Neural Networks
• Sentiment Analysis
• Sequence Labeling

Innovation

• Spiking Neural Networks
• Aspect Term Extraction
• Energy Efficiency
• Ternary Spiking Neurons
• Pseudo-gradient Training