Context-aware Stand-alone Neural Spelling Correction
This work addresses the vulnerability of natural language processing systems to misspellings, offering a solution for applications requiring robust text processing, though it is incremental as it builds on pre-trained language models.
The paper tackles the stand-alone spelling correction problem by using spelling information and global context representations to detect and correct misspellings as a sequence labeling task, achieving a 12.8% absolute F0.5 score improvement over previous state-of-the-art results.
Existing natural language processing systems are vulnerable to noisy inputs resulting from misspellings. On the contrary, humans can easily infer the corresponding correct words from their misspellings and surrounding context. Inspired by this, we address the stand-alone spelling correction problem, which only corrects the spelling of each token without additional token insertion or deletion, by utilizing both spelling information and global context representations. We present a simple yet powerful solution that jointly detects and corrects misspellings as a sequence labeling task by fine-turning a pre-trained language model. Our solution outperforms the previous state-of-the-art result by 12.8% absolute F0.5 score.