@unpublished{DeenPielkaHeesetal.2023,
  author    = {Deen, Mohammad Majd Saad Al and Pielka, Maren and Hees, J{\"o}rn and Abdou, Bouthaina Soulef and Sifa, Rafet},
  title     = {Improving Natural Language Inference in Arabic using Transformer Models and Linguistically Informed Pre-Training},
  doi       = {10.48550/arXiv.2307.14666},
  institution = {Fachbereich Informatik},
  year      = {2023},
  abstract  = {This 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 pre-training 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 multi-task pre-training in this context.},
  language  = {en}
}