Inkorrect: Online Handwriting Spelling Correction
This addresses spelling correction in digital ink for users, but appears incremental as it builds on existing work with new metrics and a trade-off analysis.
The paper tackles the problem of online handwriting spelling correction by introducing Inkorrect, a method that does not require multiple writer samples or character segmentation, and shows it outperforms prior work on a Pareto frontier between similarity and recognizability.
We introduce Inkorrect, a data- and label-efficient approach for online handwriting (Digital Ink) spelling correction - DISC. Unlike previous work, the proposed method does not require multiple samples from the same writer, or access to character level segmentation. We show that existing automatic evaluation metrics do not fully capture and are not correlated with the human perception of the quality of the spelling correction, and propose new ones that correlate with human perception. We additionally surface an interesting phenomenon: a trade-off between the similarity and recognizability of the spell-corrected inks. We further create a family of models corresponding to different points on the Pareto frontier between those two axes. We show that Inkorrect's Pareto frontier dominates the points that correspond to prior work.