Scaling BERT Models for Turkish Automatic Punctuation and Capitalization Correction

TL;DR

This study evaluates various sizes of BERT models for automatic punctuation and capitalization correction in Turkish, demonstrating that larger models improve accuracy and readability while considering computational efficiency.

Contribution

It introduces a systematic comparison of BERT model sizes for Turkish text correction, providing insights into their performance and practical deployment considerations.

Findings

Larger models achieve higher correction accuracy.

Base model attains the highest precision.

Performance scales with model size.

Abstract

This paper investigates the effectiveness of BERT based models for automated punctuation and capitalization corrections in Turkish texts across five distinct model sizes. The models are designated as Tiny, Mini, Small, Medium, and Base. The design and capabilities of each model are tailored to address the specific challenges of the Turkish language, with a focus on optimizing performance while minimizing computational overhead. The study presents a systematic comparison of the performance metrics precision, recall, and F1 score of each model, offering insights into their applicability in diverse operational contexts. The results demonstrate a significant improvement in text readability and accuracy as model size increases, with the Base model achieving the highest correction precision. This research provides a comprehensive guide for selecting the appropriate model size based on specific user needs and computational resources, establishing a framework for deploying these models in real-world applications to enhance the quality of written Turkish.