Named entity recognition (NER) is a significant natural language processing task (NLP) in several applications, including question-answering and data retrieval. NER's primary goal is to classify, discover, and extract named entities into predetermined classes: location, person, and organization. Arabic NER is a tedious process due to its unique characteristics and complexity. Unlike Classical Arabic, the earlier study on deep learning (DL)-Arabic NER focuses on modern standard Arabic (MSA) and dialectal Arabic. The transformers and recurrent neural networks (RNNs) are DL approaches that have accomplished extraordinary results in many NLP tasks since they do not trust huge knowledge sources or handcrafted features. Thus, this study introduces a novel Northern Goshawk Optimization with Artificial Intelligence for Arabic Named Entity Recognition (NGOAI-ANER) technique in Moroccan Dialect. The NGOAI-ANER technique enhanced the precision and efficiency of NER systems for Arabic text. The NGOAI-ANER technique begins by applying word embedding methods to convert text into dense vector representations, effectively capturing the semantic information essential for NER tasks. Furthermore, the stacked attention long short-term memory (SALSTM) technique is trained on the embedded data, leveraging the strength of DL architectures to identify named entities within Arabic text accurately. The NGOAI-ANER technique utilizes the northern goshawk optimization (NGO) model to fine-tune hyperparameters effectively to optimize the solution of the DL technique. An experimental assessment of the DarNERcorp dataset demonstrates the efficacy and scalability of the NGOAI-ANER model. The experimentation of the NGOAI-ANER model demonstrated a superior accuracy value of 97.86% over existing approaches.
SUBAIT et al. (Fri,) studied this question.