Logo image
Back
Efficient aspect term extraction using spiking neural network
Journal article   Open access   Peer reviewed

Efficient aspect term extraction using spiking neural network

Abhishek Kumar Mishra, Arya Somasundaram, Anup Das and Nagarajan Kandasamy
Neuromorphic computing and engineering, v 6(2), 024014
01 Jun 2026
DOI: https://doi.org/10.1088/2634-4386/ae65d6
Featured in Collection :   Research Supported by Drexel Libraries' OA Programs
url
https://doi.org/10.1088/2634-4386/ae65d6View
Published, Version of Record (VoR) Open Access via Drexel Libraries Read and Publish Program 2026 Open CC BY V4.0

Abstract

Engineering, Electrical & Electronic Physics, Applied Science & Technology Engineering Physical Sciences Physics Technology
Aspect term extraction (ATE) identifies aspect terms in review sentences, a key subtask of sentiment analysis. It is a sequence labeling task that aims to identify aspect expressions within opinionated text. While most existing approaches predominantly rely on deep neural networks (DNNs), which achieve strong performance but incur high computational and energy costs. In this work, we propose SpikeATE, an energy-efficient alternative using spiking neural networks (SNNs), which leverage sparse activations and event-driven computation to capture temporal dependencies between words, making them suitable for ATE. SpikeATE employs ternary spiking neurons and direct spike-based training with surrogate gradients to enable efficient end-to-end learning. We evaluate our approach on four SemEval benchmark datasets: Laptop14, Restaurant14, Restaurant15, and Restaurant16. Experimental results show that SpikeATE achieves competitive performance with state-of-the-art methods, obtaining F1-scores of 84.02, 86.46, 72.25, and 78.19, respectively, with the ternary model. In addition to performance, we provide a theoretical analysis of energy consumption, demonstrating the efficiency of the proposed approach. SpikeATE achieves significantly lower power usage (2.5946 mJ for the ternary model and 1.8943 mJ for the binary model) compared to transformer-based models such as BERT and self-training (approximate to 95.5 mJ) and large language models such as GPT-3.5 ( approximate to 3.92 & times;1015 mJ). These results highlight that SpikeATE reduces energy consumption by orders of magnitude while maintaining competitive performance. Overall, this work demonstrates that SNN-based architectures provide a practical and sustainable alternative to conventional DNNs for ATE, achieving a favorable balance between accuracy and computational efficiency.

Metrics

1 Record Views

Details

Logo image