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

TL;DR

KAConvText introduces a novel convolutional approach for Burmese sentence classification, effectively handling imbalanced and multiclass tasks with improved accuracy and interpretability.

Contribution

This work is the first to apply Kolmogorov-Arnold Convolution to Burmese text classification, demonstrating its effectiveness across multiple tasks and embedding configurations.

Findings

KAConvText-MLP with fine-tuned fastText embeddings achieved over 91% accuracy in hate speech detection.

The model attained over 92% accuracy in news classification.

Language identification accuracy reached 99.82%.

Abstract

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.