Context-Sensitive Spelling Correction of Clinical Text via Conditional Independence

Abstract

Spelling correction is a particularly important problem in clinical natural language processing because of the abundant occurrence of misspellings in medical records. However, the scarcity of labeled datasets in a clinical context makes it hard to build a machine learning system for such clinical spelling correction. In this work, we present a probabilistic model of correcting misspellings based on a simple conditional independence assumption, which leads to a modular decomposition into a language model and a corruption model. With a deep character-level language model trained on a large clinical corpus, and a simple edit-based corruption model, we can build a spelling correction model with small or no real data. Experimental results show that our model significantly outperforms baselines on two healthcare spelling correction datasets.

Cite

Text

Kim et al. "Context-Sensitive Spelling Correction of Clinical Text via Conditional Independence." Proceedings of the Conference on Health, Inference, and Learning, 2022.

Markdown

[Kim et al. "Context-Sensitive Spelling Correction of Clinical Text via Conditional Independence." Proceedings of the Conference on Health, Inference, and Learning, 2022.](https://mlanthology.org/chil/2022/kim2022chil-contextsensitive/)

BibTeX

@inproceedings{kim2022chil-contextsensitive,
  title     = {{Context-Sensitive Spelling Correction of Clinical Text via Conditional Independence}},
  author    = {Kim, Juyong and Weiss, Jeremy C and Ravikumar, Pradeep},
  booktitle = {Proceedings of the Conference on Health, Inference, and Learning},
  year      = {2022},
  pages     = {234-247},
  volume    = {174},
  url       = {https://mlanthology.org/chil/2022/kim2022chil-contextsensitive/}
}