# Synthetic Error Dataset Generation Mimicking Bengali Writing Pattern

arXiv: https://arxiv.org/abs/2003.03484 · HTML: https://mlsanity.com/paper/2003.03484/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Mar 2020.

## Built on by (most cited first, 4 of 4)

- [Bengali Common Voice Speech Dataset for Automatic Speech Recognition](https://mlsanity.com/paper/2206.14053/) (2022)
- [BSpell: A CNN-Blended BERT Based Bangla Spell Checker](https://mlsanity.com/paper/2208.09709/) (2022)
- [Paradigm Shift in Language Modeling: Revisiting CNN for Modeling Sanskrit Originated Bengali and Hindi Language](https://mlsanity.com/paper/2110.13032/) (2021)
- [Beyond Clean Text: Evaluating Encoder and Decoder Robustness for Bangla Event Detection in Noisy Text](https://mlsanity.com/paper/2606.30914/) (2026)

## Abstract (arXiv)

While writing Bengali using English keyboard, users often make spelling mistakes. The accuracy of any Bengali spell checker or paragraph correction module largely depends on the kind of error dataset it is based on. Manual generation of such error dataset is a cumbersome process. In this research, We present an algorithm for automatic misspelled Bengali word generation from correct word through analyzing Bengali writing pattern using QWERTY layout English keyboard. As part of our analysis, we have formed a list of most commonly used Bengali words, phonetically similar replaceable clusters, frequently mispressed replaceable clusters, frequently mispressed insertion prone clusters and some rules for Juktakkhar (constant letter clusters) handling while generating errors.