Country-level Arabic dialect identification using RNNs with and without linguistic features

Elsayed Issa, Mohammed AlShakhori, Reda Al-Bahrani, Gus Hahn-Powell

Research output: Chapter in Book/Report/Conference proceedingConference contribution

7 Scopus citations

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.

Original languageEnglish (US)
Title of host publicationWANLP 2021 - 6th Arabic Natural Language Processing Workshop, Proceedings of the Workshop
EditorsNizar Habash, Houda Bouamor, Hazem Hajj, Walid Magdy, Wajdi Zaghouani, Fethi Bougares, Nadi Tomeh, Ibrahim Abu Farha, Samia Touileb
PublisherAssociation for Computational Linguistics (ACL)
Pages276-281
Number of pages6
ISBN (Electronic)9781954085091
StatePublished - 2021
Event6th Arabic Natural Language Processing Workshop, WANLP 2021 - Virtual, Kyiv, Ukraine
Duration: Apr 19 2021 → …

Publication series

NameWANLP 2021 - 6th Arabic Natural Language Processing Workshop, Proceedings of the Workshop

Conference

Conference6th Arabic Natural Language Processing Workshop, WANLP 2021
Country/TerritoryUkraine
CityVirtual, Kyiv
Period4/19/21 → …

ASJC Scopus subject areas

  • Language and Linguistics
  • Computational Theory and Mathematics
  • Software
  • Linguistics and Language

Fingerprint

Dive into the research topics of 'Country-level Arabic dialect identification using RNNs with and without linguistic features'. Together they form a unique fingerprint.

Cite this