Adapting MARBERT for Improved Arabic Dialect Identification: Submission to the NADI 2021 Shared Task
2021-03-01EACL (WANLP) 2021Code Available0· sign in to hype
Badr AlKhamissi, Mohamed Gabr, Muhammad ElNokrashy, Khaled Essam
Code Available — Be the first to reproduce this paper.
ReproduceCode
- github.com/mohamedgabr96/NeuralDialectDetectorOfficialIn paperpytorch★ 3
Abstract
In this paper, we tackle the Nuanced Arabic Dialect Identification (NADI) shared task (Abdul-Mageed et al., 2021) and demonstrate state-of-the-art results on all of its four subtasks. Tasks are to identify the geographic origin of short Dialectal (DA) and Modern Standard Arabic (MSA) utterances at the levels of both country and province. Our final model is an ensemble of variants built on top of MARBERT that achieves an F1-score of 34.03% for DA at the country-level development set -- an improvement of 7.63% from previous work.