@InProceedings{samih-EtAl:2017:CoNLL,
  author    = {Samih, Younes  and  Eldesouki, Mohamed  and  Attia, Mohammed  and  Darwish, Kareem  and  Abdelali, Ahmed  and  Mubarak, Hamdy  and  Kallmeyer, Laura},
  title     = {Learning from Relatives: Unified Dialectal Arabic Segmentation},
  booktitle = {Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017)},
  month     = {August},
  year      = {2017},
  address   = {Vancouver, Canada},
  publisher = {Association for Computational Linguistics},
  pages     = {432--441},
  abstract  = {Arabic dialects do not just share a common koin\'{e}, but there are shared
	pan-dialectal linguistic phenomena that allow computational models for dialects
	to learn from each other. In this paper we build a unified segmentation model
	where the training data for different dialects are combined and a single model
	is trained. The model yields higher accuracies than dialect-specific models,
	eliminating the need for dialect identification before segmentation. We also
	measure the degree of relatedness between four major Arabic dialects by testing
	how a segmentation model trained on one dialect performs on the other dialects.
	We found that linguistic relatedness is contingent with geographical proximity.
	In our experiments we use SVM-based ranking and bi-LSTM-CRF sequence labeling.},
  url       = {http://aclweb.org/anthology/K17-1043}
}