KAConvText: Novel Approach to Burmese Sentence Classification using Kolmogorov-Arnold Convolution

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Thu, Ye Kyaw, Aung, Thura, Oo, Thazin Myint, Supnithi, Thepchai
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912473009881088
author Thu, Ye Kyaw
Aung, Thura
Oo, Thazin Myint
Supnithi, Thepchai
author_facet Thu, Ye Kyaw
Aung, Thura
Oo, Thazin Myint
Supnithi, Thepchai
contents This paper presents the first application of Kolmogorov-Arnold Convolution for Text (KAConvText) in sentence classification, addressing three tasks: imbalanced binary hate speech detection, balanced multiclass news classification, and imbalanced multiclass ethnic language identification. We investigate various embedding configurations, comparing random to fastText embeddings in both static and fine-tuned settings, with embedding dimensions of 100 and 300 using CBOW and Skip-gram models. Baselines include standard CNNs and CNNs augmented with a Kolmogorov-Arnold Network (CNN-KAN). In addition, we investigated KAConvText with different classification heads - MLP and KAN, where using KAN head supports enhanced interpretability. Results show that KAConvText-MLP with fine-tuned fastText embeddings achieves the best performance of 91.23% accuracy (F1-score = 0.9109) for hate speech detection, 92.66% accuracy (F1-score = 0.9267) for news classification, and 99.82% accuracy (F1-score = 0.9982) for language identification.
format Preprint
id arxiv_https___arxiv_org_abs_2507_06753
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle KAConvText: Novel Approach to Burmese Sentence Classification using Kolmogorov-Arnold Convolution
Thu, Ye Kyaw
Aung, Thura
Oo, Thazin Myint
Supnithi, Thepchai
Computation and Language
Artificial Intelligence
I.2.7; I.2.6
This paper presents the first application of Kolmogorov-Arnold Convolution for Text (KAConvText) in sentence classification, addressing three tasks: imbalanced binary hate speech detection, balanced multiclass news classification, and imbalanced multiclass ethnic language identification. We investigate various embedding configurations, comparing random to fastText embeddings in both static and fine-tuned settings, with embedding dimensions of 100 and 300 using CBOW and Skip-gram models. Baselines include standard CNNs and CNNs augmented with a Kolmogorov-Arnold Network (CNN-KAN). In addition, we investigated KAConvText with different classification heads - MLP and KAN, where using KAN head supports enhanced interpretability. Results show that KAConvText-MLP with fine-tuned fastText embeddings achieves the best performance of 91.23% accuracy (F1-score = 0.9109) for hate speech detection, 92.66% accuracy (F1-score = 0.9267) for news classification, and 99.82% accuracy (F1-score = 0.9982) for language identification.
title KAConvText: Novel Approach to Burmese Sentence Classification using Kolmogorov-Arnold Convolution
topic Computation and Language
Artificial Intelligence
I.2.7; I.2.6
url https://arxiv.org/abs/2507.06753