KoGEC : Korean Grammatical Error Correction with Pre-trained Translation Models

TL;DR

KoGEC is a Korean grammatical error correction system that fine-tunes pre-trained translation models, outperforming large language models in accuracy and error diversity, and includes a user-friendly Chrome extension.

Contribution

This paper introduces KoGEC, a novel Korean GEC system based on fine-tuned NLLB models, demonstrating superior performance and balanced error correction compared to large language models.

Findings

Fine-tuned NLLB models outperform GPT-4 and HCX-3 in Korean GEC.

KoGEC achieves a balanced correction across various error types.

Vocabulary expansion decreases model performance.

Abstract

This research introduces KoGEC, a Korean Grammatical Error Correction system using pre\--trained translation models. We fine-tuned NLLB (No Language Left Behind) models for Korean GEC, comparing their performance against large language models like GPT-4 and HCX-3. The study used two social media conversation datasets for training and testing. The NLLB models were fine-tuned using special language tokens to distinguish between original and corrected Korean sentences. Evaluation was done using BLEU scores and an "LLM as judge" method to classify error types. Results showed that the fine-tuned NLLB (KoGEC) models outperformed GPT-4o and HCX-3 in Korean GEC tasks. KoGEC demonstrated a more balanced error correction profile across various error types, whereas the larger LLMs tended to focus less on punctuation errors. We also developed a Chrome extension to make the KoGEC system accessible to users. Finally, we explored token vocabulary expansion to further improve the model but found it to decrease model performance. This research contributes to the field of NLP by providing an efficient, specialized Korean GEC system and a new evaluation method. It also highlights the potential of compact, task-specific models to compete with larger, general-purpose language models in specialized NLP tasks.