Spelling Error Correction Using a Nested RNN Model and Pseudo Training Data
This addresses spelling correction for English users, but it is incremental as it builds on existing RNN approaches.
The paper tackled English spelling error correction by proposing a nested RNN model trained with pseudo data based on phonetic similarity, achieving superior performance compared to existing systems.
We propose a nested recurrent neural network (nested RNN) model for English spelling error correction and generate pseudo data based on phonetic similarity to train it. The model fuses orthographic information and context as a whole and is trained in an end-to-end fashion. This avoids feature engineering and does not rely on a noisy channel model as in traditional methods. Experiments show that the proposed method is superior to existing systems in correcting spelling errors.