Contextual Spelling Correction with Language Model for Low-resource Setting

TL;DR

This paper introduces a novel approach for low-resource language spell correction by combining a small transformer language model with an unsupervised error model within a noisy channel framework, demonstrated on Nepali.

Contribution

It presents a new low-resource spell correction method using a small transformer LM and unsupervised error modeling, addressing data scarcity challenges.

Findings

Effective correction on Nepali with limited data

Combines language model and error rules successfully

Outperforms baseline methods in low-resource setting

Abstract

The task of Spell Correction(SC) in low-resource languages presents a significant challenge due to the availability of only a limited corpus of data and no annotated spelling correction datasets. To tackle these challenges a small-scale word-based transformer LM is trained to provide the SC model with contextual understanding. Further, the probabilistic error rules are extracted from the corpus in an unsupervised way to model the tendency of error happening(error model). Then the combination of LM and error model is used to develop the SC model through the well-known noisy channel framework. The effectiveness of this approach is demonstrated through experiments on the Nepali language where there is access to just an unprocessed corpus of textual data.