ABB-BERT: A BERT-based Model for Spelling Correction
ABB-BERT: A BERT model for disambiguating abbreviations and contractions
Abbreviations and contractions are commonly found in text across different domains and people.Existing spelling correction models are not suitable to handle expansions because of many reductions of characters in words.In this work, we propose a new model, called abb-bert, which deals with an ambiguous language containing abbreviations and contractions.It can rank them from thousands of options and is designed for scale.It is trained on wikipedia text, and the algorithm allows it to be fine-tuned with little compute to get better performance for a domain or person.
