Spelling Correction as a Foreign Language
This approach simplifies spelling correction for applications like text processing by eliminating the need for separate language and error models, though it is incremental in applying existing neural methods to this domain.
The paper tackled spelling correction by reformulating it as a machine translation task using an encoder-decoder framework, achieving competitive performance with state-of-the-art methods without requiring feature engineering or manual tuning.
In this paper, we reformulated the spell correction problem as a machine translation task under the encoder-decoder framework. This reformulation enabled us to use a single model for solving the problem that is traditionally formulated as learning a language model and an error model. This model employs multi-layer recurrent neural networks as an encoder and a decoder. We demonstrate the effectiveness of this model using an internal dataset, where the training data is automatically obtained from user logs. The model offers competitive performance as compared to the state of the art methods but does not require any feature engineering nor hand tuning between models.