Leveraging LLMs for Bangla Grammar Error Correction: Error Categorization, Synthetic Data, and Model Evaluation

ACL ARR 2025 February Submission6359 Authors

Abstract: Large Language Models (LLMs) perform exceedingly well in Natural Language Understanding (NLU) tasks for many languages including English. However, despite being the fifth most-spoken language globally, Grammatical Error Correction (GEC) in Bangla remains underdeveloped. In this work, we investigate how LLMs can be leveraged for improving Bangla GEC. For that, we first do an extensive categorization of 12 error classes in Bangla, and take a survey of native Bangla speakers to collect real-world errors. We next devise a rule-based noise injection method to create grammatically incorrect sentences corresponding to correct ones. The Vaiyākaraṇa dataset, thus created, consists of 567,422 sentences of which 227,119 are erroneous. This dataset is then used to instruction-tune LLMs for the task of GEC in Bangla. Evaluations show that instruction-tuning with Vaiyākaraṇa improves GEC performance of LLMs by 3-7 percentage points as compared to zero-shot setting, and makes them achieve human-like performance in error identification. Humans, though, remain superior in grammatical error correction.

Paper Type: Long

Research Area: Resources and Evaluation

Research Area Keywords: corpus creation; benchmarking; language resources;automatic creation and evaluation of language resources; datasets for low resource languages

Contribution Types: Approaches to low-resource settings, Data resources, Data analysis

Languages Studied: Bangla or Bengali

Submission Number: 6359