@InProceedings{farag-rei-briscoe:2017:BEA,
  author    = {Farag, Youmna  and  Rei, Marek  and  Briscoe, Ted},
  title     = {An Error-Oriented Approach to Word Embedding Pre-Training},
  booktitle = {Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications},
  month     = {September},
  year      = {2017},
  address   = {Copenhagen, Denmark},
  publisher = {Association for Computational Linguistics},
  pages     = {149--158},
  abstract  = {We propose a novel word embedding pre-training approach that exploits writing
	errors in learners' scripts. We compare our method to previous models that tune
	the embeddings based on script scores and the discrimination between correct
	and corrupt word contexts in addition to the generic commonly-used embeddings
	pre-trained on large corpora. The comparison is achieved by using the
	aforementioned models to bootstrap a neural network that learns to predict a
	holistic score for scripts. Furthermore, we investigate augmenting our model
	with error corrections and monitor the impact on performance. Our results show
	that our error-oriented approach outperforms other comparable ones which is
	further demonstrated when training on more data. Additionally, extending the
	model with corrections provides further performance gains when data sparsity is
	an issue.},
  url       = {http://www.aclweb.org/anthology/W17-5016}
}