Contextual Spelling Correction with Language Model for Low-resource Setting
This addresses spelling correction for low-resource languages like Nepali, but it is incremental as it adapts the noisy channel framework with existing methods.
The paper tackled spelling correction in low-resource languages by training a small transformer language model and extracting unsupervised error rules, achieving effectiveness demonstrated on Nepali with limited data.
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.