Robsut Wrod Reocginiton via semi-Character Recurrent Neural Network
This work addresses the problem of improving computational word recognition robustness for applications like spelling correction, though it is incremental as it builds on known neural network methods.
The paper tackled robust word recognition under letter jumbling noise, inspired by the Cambridge University effect, and demonstrated that their semi-character RNN model significantly outperforms existing spelling checkers and character-based CNNs in spelling correction tasks.
Language processing mechanism by humans is generally more robust than computers. The Cmabrigde Uinervtisy (Cambridge University) effect from the psycholinguistics literature has demonstrated such a robust word processing mechanism, where jumbled words (e.g. Cmabrigde / Cambridge) are recognized with little cost. On the other hand, computational models for word recognition (e.g. spelling checkers) perform poorly on data with such noise. Inspired by the findings from the Cmabrigde Uinervtisy effect, we propose a word recognition model based on a semi-character level recurrent neural network (scRNN). In our experiments, we demonstrate that scRNN has significantly more robust performance in word spelling correction (i.e. word recognition) compared to existing spelling checkers and character-based convolutional neural network. Furthermore, we demonstrate that the model is cognitively plausible by replicating a psycholinguistics experiment about human reading difficulty using our model.