Saad Al Deen, Mohammad MajdMohammad MajdSaad Al DeenPielka, MarenMarenPielkaHees, JörnJörnHeesAbdou, Bouthaina SoulefBouthaina SoulefAbdouSifa, RafetRafetSifa2024-01-312024-01-312023https://publica.fraunhofer.de/handle/publica/45952510.1109/SSCI52147.2023.103718912-s2.0-85182925537This paper addresses the classification of Arabic text data in the field of Natural Language Processing (NLP), with a particular focus on Natural Language Inference (NLI) and Contradiction Detection (CD). Arabic is considered a resource-poor language, meaning that there are few data sets available, which leads to limited availability of NLP methods. To overcome this limitation, we create a dedicated data set from publicly available resources. Subsequently, transformer-based machine learning models are being trained and evaluated. We find that a language-specific model (AraBERT) performs competitively with state-of-the-art multilingual approaches, when we apply linguistically informed pretraining methods such as Named Entity Recognition (NER). To our knowledge, this is the first large-scale evaluation for this task in Arabic, as well as the first application of multitask pretraining in this context.enComputational modelingMachine learningTransformersNatural language processingNatural language processingComputational intelligenceconference paper