Work

TF-IDF or Transformers for Arabic Dialect Identification? ITFLOWS participation in the NADI 2022 Shared Task

Year: 2022

Type: conference-paper

Abstract: This study targets the shared task of Nuanced Arabic Dialect Identification (NADI) organized with the Workshop on Arabic Natural Language Processing (WANLP).It further focuses on Subtask 1: the identification of the Arabic dialects at the country level.More specifically, it studies the impact of a traditional approach such as TF-IDF and then moves on to study the impact of advanced deep learning based methods.These methods include fully finetuning MARBERT as well as adapter based fine-tuning of MARBERT with and without performing data augmentation.The evaluation shows that the traditional approach based on TF-IDF scores the best in terms of accuracy on TEST-A dataset, while, the fine-tuned MAR-BERT with adapter on augmented data scores the second on Macro F1-score on the TEST-B dataset.This led to the proposed system being ranked second on the shared task on average.

Source: Arabic Natural Language Processing Workshop (WANLP)

DOI: 10.18653/v1/2022.wanlp-1.42

Authors: Fouad Shammary, Yiyi Chen, Zsolt T Kardkovacs, Mehwish Alam, Haithem Afli

Institutions: Munster Technological University, Karlsruhe Institute of Technology, FIZ Karlsruhe – Leibniz Institute for Information Infrastructure

Language: English

Topic: Natural Language Processing Techniques

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: Science Foundation Ireland

Award: ADAPT_Phase 2