Spelling correction is the task of detecting and correcting spelling mistakes.
We present an approach to training neural networks to generate sequences using actor-critic methods from reinforcement learning (RL).
#7 best model for Machine Translation on IWSLT2015 English-German
We present an unsupervised context-sensitive spelling correction method for clinical free-text that uses word and character n-gram embeddings.
Phonetic similarity algorithms identify words and phrases with similar pronunciation which are used in many natural language processing tasks.
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 this paper, we cast the CWS as a sequence translation problem and propose a novel sequence-to-sequence CWS model with an attention-based encoder-decoder framework.
We show that MoNoise beats the state-of-the-art on different normalization benchmarks for English and Dutch, which all define the task of normalization slightly different.
SOTA for Lexical Normalization on LexNorm