Recurrent Neural Networks (RNNs) and transformers are deep learning models that have achieved remarkable success in several Natural Language Processing (NLP) tasks since they do not rely on handcrafted features nor enormous knowledge resources. Named Entity Recognition (NER) is an essential NLP task that is used in many applications such as information retrieval, question answering, and machine translation. NER aims to locate, extract, and classify named entities into predefined categories such as person, organization and location. Arabic NER is considered a challenging task because of the complexity and the unique characteristics of Arabic. Most of the previous research on deep learning based-Arabic NER focused on Modern Standard Arabic and Dialectal Arabic, which are different variations from Classical Arabic. In this paper, we investigate deep learning-based Classical Arabic NER using different deep neural network architectures and a BERT based contextual language model that is trained on general domain Arabic text. We propose two RNN-based models by fine-tunning the pretrained BERT language model to recognize and classify named entities from Classical Arabic. The pre-trained BERT contextual language model representations were used as input features to a BGRU/BLSTM model and were fine-tuned using a Classical Arabic NER dataset. In addition, we explore variant architectures of the proposed BERT-BGRU/BLSTM-CRF models. Experimentations showed that the BERT-BGRU-CRF model outperformed the other models by achieving an F-measure of 94.76% on the CANERCorpus. To the best of our knowledge, this is the first work that aims to recognize named entities in Classical Arabic using deep learning.

No abstract

Purpose Sickle cell disease (SCD) is a significant burden for patients and healthcare systems due to multiple factors, including high readmission rates. This study aimed to determine the general characteristics, etiology of admissions, annual admission rate, length of stay, and readmission rate of patients with SCD. Patients and Methods This retrospective observational study included all adult patients with SCD admitted to the General Internal Medicine (GIM) unit between 2016 and 2021. Results There were 160 patients (mean age, 31.08 ± 9.06 years; 51.25% female) with SCD included in this study. Most originated from southern Saudi Arabia (45.62%). The average annual number of emergency department (ED) visits was 4, and approximately 19% of patients had ≥3 annual admissions. The mean length of stay was 6 days. The readmission rates at 7, 30, 60, and 90 days were 8%, 24.5%, 13.6%, and 10.8%, respectively. Conclusion SCD generates a significant economic burden on the Saudi society and the effects on the healthcare system and patients’ quality of life are evident in the high ED visits, readmission rates and prolonged hospitalization. Thereupon we advocate the implementation of sickle cell disease-specialized multidisciplinary clinics.

Parsing is an essential step in most of Natural Language Processing (NLP) systems. It is mainly concerned with determining the grammatical position of each word in a sentence, and how words can be put together to form a correct sentence according to a certain grammar. In this paper, we present the architecture of a bottom-up semantic parser for traditional Arabic language. This parser is based on a Unification Based Grammar (UBG) representation of traditional Arabic grammar, and is implemented using Extensible Markup Language (XML). Moreover, we provide a set of traditional Arabic grammar rules that can be used in future results. INTRODUCTIONParsing is a technique used to discover the grammatical role of each word in a given sentence, which is considered a necessity for many NLP applications such as translation, information retrieval and question answering. It relies on two things: a grammar, which specifies the acceptable structures that can produce a correct sentence; and a parsing technique, which is the method of analyzing a sentence to determine its structure according to the given grammar.

No abstract