Grammar Error Correction using Masked Language Models

Propose a system for grammatical error correction using a masked language model. Introduce a framework consisting of two tasks: tagging, which chooses and arbitrarily reorders a subset of input tokens to keep, and insertion, which infills the missing tokens with another pretrained masked language model.

Data and Resources

Cite this as

Ng et al., Boyd, Rozovskaya and Roth (2024). Dataset: Grammar Error Correction using Masked Language Models. https://doi.org/10.57702/e8gimqyb

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2111.09280
Author Ng et al.
More Authors
Boyd
Rozovskaya and Roth
Homepage https://aclanthology.org/2014.emnlp-conference.123