Open access
Jul 2026
A Comprehensive Approach to Misspelling Correction with Contextual Word Embeddings and Levenshtein Distance
A spelling correction framework that combines contextual information from BERT masked language models with edit-distance-based candidate generation with heuristic correction strategies and a biasing mechanism that improves the model’s focus on erroneous words is proposed.
Amirreza Naziri, Hossein Zeinali
· ACM Transactions on Asian an... · 0 citations