@InProceedings{kann-EtAl:2018:N18-1,
  author    = {Kann, Katharina  and  Mager Hois, Jesus Manuel  and  Meza Ruiz, Ivan Vladimir  and  Schütze, Hinrich},
  title     = {Fortification of Neural Morphological Segmentation Models for Polysynthetic Minimal-Resource Languages},
  booktitle = {Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)},
  month     = {June},
  year      = {2018},
  address   = {New Orleans, Louisiana},
  publisher = {Association for Computational Linguistics},
  pages     = {47--57},
  abstract  = {Morphological segmentation for polysynthetic languages is challenging, because a word may consist of many individual morphemes and training data can be extremely scarce. Since neural sequence-to-sequence (seq2seq) models define the state of the art for morphological segmentation in high-resource settings and for (mostly) European languages, we first show that they also obtain competitive performance for Mexican polysynthetic languages in minimal-resource settings. We then propose two novel multi-task training approaches—one with, one without need for external unlabeled resources—, and two corresponding data augmentation methods, improving over the neural baseline for all languages. Finally, we explore cross-lingual transfer as a third way to fortify our neural model and show that we can train one single multi-lingual model for related languages while maintaining comparable or even improved performance, thus reducing the amount of parameters by close to 75%. We provide our morphological segmentation datasets for Mexicanero, Nahuatl, Wixarika and Yorem Nokki for future research.},
  url       = {http://www.aclweb.org/anthology/N18-1005}
}