Unsupervised Context-Sensitive Spelling Correction of Clinical Free-Text with Word and Character N-Gram Embeddings

Pieter Fivez, Simon Šuster, Walter Daelemans


Abstract
We present an unsupervised context-sensitive spelling correction method for clinical free-text that uses word and character n-gram embeddings. Our method generates misspelling replacement candidates and ranks them according to their semantic fit, by calculating a weighted cosine similarity between the vectorized representation of a candidate and the misspelling context. We greatly outperform two baseline off-the-shelf spelling correction tools on a manually annotated MIMIC-III test set, and counter the frequency bias of an optimized noisy channel model, showing that neural embeddings can be successfully exploited to include context-awareness in a spelling correction model.
Anthology ID:
W17-2317
Volume:
BioNLP 2017
Month:
August
Year:
2017
Address:
Vancouver, Canada,
Venue:
BioNLP
SIG:
SIGBIOMED
Publisher:
Association for Computational Linguistics
Note:
Pages:
143–148
Language:
URL:
https://aclanthology.org/W17-2317
DOI:
10.18653/v1/W17-2317
Bibkey:
Cite (ACL):
Pieter Fivez, Simon Šuster, and Walter Daelemans. 2017. Unsupervised Context-Sensitive Spelling Correction of Clinical Free-Text with Word and Character N-Gram Embeddings. In BioNLP 2017, pages 143–148, Vancouver, Canada,. Association for Computational Linguistics.
Cite (Informal):
Unsupervised Context-Sensitive Spelling Correction of Clinical Free-Text with Word and Character N-Gram Embeddings (Fivez et al., BioNLP 2017)
Copy Citation:
PDF:
https://preview.aclanthology.org/auto-file-uploads/W17-2317.pdf
Data
MIMIC-III