Bangla Grammatical Error Detection Using T5 Transformer Model
This addresses grammatical error detection for Bangla, an under-resourced language, but is incremental as it adapts an existing translation model with extensive post-processing.
The paper tackled grammatical error detection in Bangla by fine-tuning a T5 transformer model on a dataset of 9385 sentences, achieving an average Levenshtein distance of 1.0394 on a test set of 5000 sentences after post-processing.
This paper presents a method for detecting grammatical errors in Bangla using a Text-to-Text Transfer Transformer (T5) Language Model, using the small variant of BanglaT5, fine-tuned on a corpus of 9385 sentences where errors were bracketed by the dedicated demarcation symbol. The T5 model was primarily designed for translation and is not specifically designed for this task, so extensive post-processing was necessary to adapt it to the task of error detection. Our experiments show that the T5 model can achieve low Levenshtein Distance in detecting grammatical errors in Bangla, but post-processing is essential to achieve optimal performance. The final average Levenshtein Distance after post-processing the output of the fine-tuned model was 1.0394 on a test set of 5000 sentences. This paper also presents a detailed analysis of the errors detected by the model and discusses the challenges of adapting a translation model for grammar. Our approach can be extended to other languages, demonstrating the potential of T5 models for detecting grammatical errors in a wide range of languages.