@InProceedings{malinin-EtAl:2017:Short,
  author    = {Malinin, Andrey  and  Ragni, Anton  and  Knill, Kate  and  Gales, Mark},
  title     = {Incorporating Uncertainty into Deep Learning for Spoken Language Assessment},
  booktitle = {Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)},
  month     = {July},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {45--50},
  abstract  = {There is a growing demand for automatic assessment of spoken English
	proficiency. These systems need to handle large variations in input
	data owing to the wide range of candidate skill levels and L1s, and
	errors from ASR. Some candidates will be a poor match
	to the training data set, undermining the validity of the predicted grade. For
	high stakes tests it is essential for such systems not only to grade well, but
	also to provide a measure
	of their uncertainty in their predictions, enabling rejection to human
	graders. Previous work examined Gaussian Process (GP) graders which, though
	successful, do not scale well with large data sets. Deep Neural Network (DNN)
	may also be used to provide uncertainty using Monte-Carlo Dropout (MCD). This
	paper proposes a novel method to yield uncertainty and compares it to GPs and
	DNNs with MCD. The proposed approach explicitly teaches a DNN to have low
	uncertainty on training data and high uncertainty on generated artificial data.
	On experiments conducted on data from the Business Language Testing Service
	(BULATS), the proposed approach is found to outperform GPs and DNNs with MCD in
	uncertainty-based rejection whilst achieving comparable grading performance.},
  url       = {http://aclweb.org/anthology/P17-2008}
}