@inproceedings{d39b6677fb8944689369f4110af2c6c2,
title = "Country-level Arabic dialect identification using RNNs with and without linguistic features",
abstract = "This work investigates the value of augmenting recurrent neural networks with feature engineering for the Second Nuanced Arabic Dialect Identification (NADI) Subtask 1.2: Country-level DA identification. We compare the performance of a simple word-level LSTM using pretrained embeddings with one enhanced using feature embeddings for engineered linguistic features. Our results show that the addition of explicit features to the LSTM is detrimental to performance. We attribute this performance loss to the bivalency of some linguistic items in some text, ubiquity of topics, and participant mobility.",
author = "Elsayed Issa and Mohammed AlShakhori and Reda Al-Bahrani and Gus Hahn-Powell",
note = "Publisher Copyright: {\textcopyright} WANLP 2021 - 6th Arabic Natural Language Processing Workshop; 6th Arabic Natural Language Processing Workshop, WANLP 2021 ; Conference date: 19-04-2021",
year = "2021",
language = "English (US)",
series = "WANLP 2021 - 6th Arabic Natural Language Processing Workshop, Proceedings of the Workshop",
publisher = "Association for Computational Linguistics (ACL)",
pages = "276--281",
editor = "Nizar Habash and Houda Bouamor and Hazem Hajj and Walid Magdy and Wajdi Zaghouani and Fethi Bougares and Nadi Tomeh and Farha, {Ibrahim Abu} and Samia Touileb",
booktitle = "WANLP 2021 - 6th Arabic Natural Language Processing Workshop, Proceedings of the Workshop",
}