Efficient Aspect Term Extraction using Spiking Neural Network

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Mishra, Abhishek Kumar, Somasundaram, Arya, Das, Anup, Kandasamy, Nagarajan
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914245435719680
author Mishra, Abhishek Kumar
Somasundaram, Arya
Das, Anup
Kandasamy, Nagarajan
author_facet Mishra, Abhishek Kumar
Somasundaram, Arya
Das, Anup
Kandasamy, Nagarajan
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_06637
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Efficient Aspect Term Extraction using Spiking Neural Network
Mishra, Abhishek Kumar
Somasundaram, Arya
Das, Anup
Kandasamy, Nagarajan
Computation and Language
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.
title Efficient Aspect Term Extraction using Spiking Neural Network
topic Computation and Language
url https://arxiv.org/abs/2601.06637