Vector representation of non-standard spellings using dynamic time warping and a denoising autoencoder

@article{Lazreg2017VectorRO,
  title={Vector representation of non-standard spellings using dynamic time warping and a denoising autoencoder},
  author={Mehdi Ben Lazreg and Morten Goodwin Olsen and Ole-Christoffer Granmo},
  journal={2017 IEEE Congress on Evolutionary Computation (CEC)},
  year={2017},
  pages={1444-1450}
}
The presence of non-standard spellings in Twitter causes challenges for many natural language processing tasks. Traditional approaches mainly regard the problem as a translation, spell checking, or speech recognition problem. This paper proposes a method that represents the stochastic relationship between words and their non-standard versions in real vectors. The method uses dynamic time warping to preprocess the non-standard spellings and autoencoder to derive the vector representation. The… CONTINUE READING