Efficient Aspect Term Extraction using Spiking Neural Network

Abhishek Kumar Mishra, Arya Somasundaram, Anup Das, Nagarajan Kandasamy
1/10/2026
cs.CL

No official code found. Best implementation: abhishekkumarm98/SpikeATE (4 stars, last commit 2026-01-10).

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.

View on arXivView PDF

Code Implementations(1)

abhishekkumarm98/SpikeATECommunity67%

Efficient Aspect Term Extraction using Spiking Neural Network

40Python, Jupyter NotebookOct 9, 20249 months ago

Similar Papers

SNNLP: Energy-Efficient Natural Language Processing Using Spiking Neural Networks

82% match1 repo62024

Leveraging Deep Neural Networks for Aspect-Based Sentiment Classification

81% match2025

Supervised Gradual Machine Learning for Aspect Category Detection

81% match2024

Spiking Convolutional Neural Networks for Text Classification

80% match1 repo342024

Enhancing Long-Range Dependency with State Space Model and Kolmogorov-Arnold Networks for Aspect-Based Sentiment Analysis

80% match2024

SpikeVoice: High-Quality Text-to-Speech Via Efficient Spiking Neural Network

79% match2024

Cite this paper

@article{mishra2026efficient,
  title  = {Efficient Aspect Term Extraction using Spiking Neural Network},
  author = {Abhishek Kumar Mishra and Arya Somasundaram and Anup Das and Nagarajan Kandasamy},
  year   = {2026},
  eprint = {2601.06637},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2601.06637v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2601.06637.svg)](https://codeofpaper.com/paper/2601.06637)

Discussion