@inproceedings{f6b6b872e5cc4782b2253102a2c93b30,
title = "A Neural Architecture for Dialectal Arabic Segmentation",
abstract = "The automated processing of Arabic dialects is challenging due to the lack of spelling standards and the scarcity of annotated data and resources in general. Segmentation of words into their constituent tokens is an important processing step for natural language processing. In this paper, we show how a segmenter can be trained on only 350 annotated tweets using neural networks without any normalization or reliance on lexical features or linguistic resources. We deal with segmentation as a sequence labeling problem at the character level. We show experimentally that our model can rival state-of-the-art methods that heavily depend on additional resources.",
author = "Younes Samih and Mohammed Attia and Mohamed Eldesouki and Hamdy Mubarak and Ahmed Abdelali and Laura Kallmeyer and Kareem Darwish",
note = "Publisher Copyright: {\textcopyright}2017 Association for Computational Linguistics; 3rd Arabic Natural Language Processing Workshop, WANLP 2017 held at EACL 2017 ; Conference date: 03-04-2017",
year = "2017",
language = "English",
series = "WANLP 2017, co-located with EACL 2017 - 3rd Arabic Natural Language Processing Workshop, Proceedings of the Workshop",
publisher = "Association for Computational Linguistics (ACL)",
pages = "46--54",
booktitle = "WANLP 2017, co-located with EACL 2017 - 3rd Arabic Natural Language Processing Workshop, Proceedings of the Workshop",
address = "United States",
}