no code implementations • COLING (WANLP) 2020 • Abdellah El Mekki, Ahmed Alami, Hamza Alami, Ahmed Khoumsi, Ismail Berrada
Around the Arab world, different Arabic dialects are spoken by more than 300M persons, and are increasingly popular in social media texts.
no code implementations • EACL (WANLP) 2021 • Abdellah El Mekki, Abdelkader El Mahdaouy, Kabil Essefar, Nabil El Mamoun, Ismail Berrada, Ahmed Khoumsi
Dialect and standard language identification are crucial tasks for many Arabic natural language processing applications.
1 code implementation • 28 Oct 2023 • Abdellah El Mekki, Muhammad Abdul-Mageed, ElMoatez Billah Nagoudi, Ismail Berrada, Ahmed Khoumsi
We also demonstrate the effectiveness of ProMap in re-ranking results from other BLI methods such as with aligned static word embeddings.
no code implementations • SemEval (NAACL) 2022 • Abdellah El Mekki, Abdelkader El Mahdaouy, Mohammed Akallouch, Ismail Berrada, Ahmed Khoumsi
This is due to the complexity and ambiguity of named entities that appear in various contexts such as short input sentences, emerging entities, and complex entities.
no code implementations • 23 Jun 2021 • Abdellah El Mekki, Abdelkader El Mahdaouy, Kabil Essefar, Nabil El Mamoun, Ismail Berrada, Ahmed Khoumsi
Dialect and standard language identification are crucial tasks for many Arabic natural language processing applications.
no code implementations • EACL (WANLP) 2021 • Abdelkader El Mahdaouy, Abdellah El Mekki, Kabil Essefar, Nabil El Mamoun, Ismail Berrada, Ahmed Khoumsi
The prominence of figurative language devices, such as sarcasm and irony, poses serious challenges for Arabic Sentiment Analysis (SA).
1 code implementation • NAACL 2021 • Abdellah El Mekki, Abdelkader El Mahdaouy, Ismail Berrada, Ahmed Khoumsi
In this paper, we propose a new unsupervised domain adaptation method for Arabic cross-domain and cross-dialect sentiment analysis from Contextualized Word Embedding.