@inproceedings{e1b47f187d844df78a43d138df79dc8d,
title = "ArBanking77: Intent Detection Neural Model and a New Dataset in Modern and Dialectical Arabic",
abstract = "This paper presents the ArBanking77, a large Arabic dataset for intent detection in the banking domain. Our dataset was arabized and localized from the original English Banking77 dataset, which consists of 13,083 queries to ArBanking77 dataset with 31,404 queries in both Modern Standard Arabic (MSA) and Palestinian dialect, with each query classified into one of the 77 classes (intents). Furthermore, we present a neural model, based on AraBERT, fine-tuned on ArBanking77, which achieved an F1-score of 0.9209 and 0.8995 on MSA and Palestinian dialect, respectively. We performed extensive experimentation in which we simulated low-resource settings, where the model is trained on a subset of the data and augmented with noisy queries to simulate colloquial terms, mistakes and misspellings found in real NLP systems, especially live chat queries. The data and the models are publicly available at https://sina.birzeit.edu/arbanking77.",
author = "Mustafa Jarrar and Ahmet Birim and Mohammed Khalilia and Mustafa Erden and Sana Ghanem",
note = "Publisher Copyright: {\textcopyright} 2023 Association for Computational Linguistics.; 1st Arabic Natural Language Processing Conference, ArabicNLP 2023 ; Conference date: 07-12-2023",
year = "2023",
month = dec,
day = "7",
language = "English",
series = "ArabicNLP 2023 - 1st Arabic Natural Language Processing Conference, Proceedings",
publisher = "Association for Computational Linguistics (ACL)",
pages = "276--287",
editor = "Hassan Sawaf and Samhaa El-Beltagy and Wajdi Zaghouani and Walid Magdy and Nadi Tomeh and \{Abu Farha\}, Ibrahim and Nizar Habash and Salam Khalifa and Amr Keleg and Hatem Haddad and Imed Zitouni and Ahmed Abdelali and Khalil Mrini and Rawan Almatham",
booktitle = "ArabicNLP 2023 - 1st Arabic Natural Language Processing Conference, Porceedings",
address = "United States",
}