@InProceedings{bollmann-sgaard-bingel:2018:W18-34,
  author    = {Bollmann, Marcel  and  Søgaard, Anders  and  Bingel, Joachim},
  title     = {Multi-task learning for historical text normalization: Size matters},
  booktitle = {Proceedings of the Workshop on Deep Learning Approaches for Low-Resource NLP},
  month     = {July},
  year      = {2018},
  address   = {Melbourne},
  publisher = {Association for Computational Linguistics},
  pages     = {19--24},
  abstract  = {Historical text normalization suffers from small datasets that exhibit high variance, and previous work has shown that multi-task learning can be used to leverage data from related problems in order to obtain more robust models. Previous work has been limited to datasets from a specific language and a specific historical period, and it is not clear whether results generalize. It therefore remains an open problem, when historical text normalization benefits from multi-task learning. We explore the benefits of multi-task learning across 10 different datasets, representing different languages and periods. Our main finding---contrary to what has been observed for other NLP tasks---is that multi-task learning mainly works when target task data is very scarce.},
  url       = {http://www.aclweb.org/anthology/W18-3403}
}