A Methodology for Generative Spelling Correction via Natural Spelling Errors Emulation across Multiple Domains and Languages

TL;DR

This paper introduces a methodology for generative spelling correction that emulates natural spelling errors across multiple languages and domains, enhancing model training and performance.

Contribution

It proposes a novel approach to emulate natural spelling errors for training generative models, including a new library called SAGE for automatic spelling correction.

Findings

Emulation of natural spelling errors improves correction accuracy.

Models trained with error emulation perform well across multiple domains.

The SAGE library facilitates effective generative spelling correction.

Abstract

Modern large language models demonstrate impressive capabilities in text generation and generalization. However, they often struggle with solving text editing tasks, particularly when it comes to correcting spelling errors and mistypings. In this paper, we present a methodology for generative spelling correction (SC), which was tested on English and Russian languages and potentially can be extended to any language with minor changes. Our research mainly focuses on exploring natural spelling errors and mistypings in texts and studying the ways those errors can be emulated in correct sentences to effectively enrich generative models' pre-train procedure. We investigate the impact of such emulations and the models' abilities across different text domains. In this work, we investigate two spelling corruption techniques: 1) first one mimics human behavior when making a mistake through leveraging statistics of errors from particular dataset and 2) second adds the most common spelling errors, keyboard miss clicks, and some heuristics within the texts. We conducted experiments employing various corruption strategies, models' architectures and sizes on the pre-training and fine-tuning stages and evaluated the models using single-domain and multi-domain test sets. As a practical outcome of our work, we introduce SAGE(Spell checking via Augmentation and Generative distribution Emulation). It is a library for automatic generative SC that includes a family of pre-trained generative models and built-in augmentation algorithms.