@inproceedings{3ad74664d41a420bb6607efe35505505,
title = "Learning from relatives: Unified dialectal Arabic segmentation",
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.",
author = "Younes Samih and Mohamed Eldesouki and Mohammed Attia and Kareem Darwish and Ahmed Abdelali and Hamdy Mubarak and Laura Kallmeyer",
note = "Publisher Copyright: {\textcopyright} 2017 Association for Computational Linguistics.; 21st Conference on Computational Natural Language Learning, CoNLL 2017 ; Conference date: 03-08-2017 Through 04-08-2017",
year = "2017",
doi = "10.18653/v1/k17-1043",
language = "English",
series = "CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings",
publisher = "Association for Computational Linguistics (ACL)",
pages = "432--441",
booktitle = "CoNLL 2017 - 21st Conference on Computational Natural Language Learning, Proceedings",
address = "United States",
}