Computer-assisted i‘raab of Arabic sentences for teaching grammar to students

Mannaa, Zarah M.; Azmi, Aqil M.; Aboalsamh, Hatim

doi:10.1016/j.jksuci.2022.08.020

Cited by 5 publications

(4 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In light of the fact that the Holy Qur'an is written in Arabic, it is crucial that we understand its meaning in its entirety. Mannaa et al (2022) devised an enhanced context-free grammar (eCFG) that covers all the rules taught in Saudi school's grammar textbooks. The eCFG eliminates the need for specialized grammar, e.g., link grammar, to resolve complex cases involving dependencies.…”

Section: Grammatical Nlp Analysismentioning

confidence: 99%

Arabic natural language processing for Qur’anic research: a systematic review

et al. 2022

Self Cite

View full text Add to dashboard Cite

The Qur’an is a fourteen centuries old divine book in Arabic language that is read and followed by almost two billion Muslims globally as their sacred religious text. With the rise of Islam, the Arabic language gained popularity and became the lingua franca for large swaths of the old world. Devout Muslims read the Qur’an daily seeking guidance and comfort. Though the Qur’an, as a text, is short, there is a huge volume of supporting work filling tens of thousands of volumes, e.g., commentaries, exegesis, etc. Recently, there has been a renewed interest in such religious texts by non-specialists. Many of which were fueled by the recent advances in computational and natural language processing (NLP) techniques. These techniques help the development of tools that benefit common people to gain knowledge easily. This paper surveys the different efforts in the field of Qur’anic NLP, serving as a synthesized compendium of works (tools, data sets, approaches) covering the gamut from automated morphological analysis to correction of Qur’anic recitation via speech recognition. Multiple approaches are discussed for several tasks, where appropriate. Finally, we outline future research directions in this field.

show abstract

Section: Grammatical Nlp Analysismentioning

confidence: 99%

Arabic natural language processing for Qur’anic research: a systematic review

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…This complexity presents formidable challenges for computational models in accurately parsing and understanding words, thereby impacting the coherence of generated story endings. Semantic Ambiguity: The semantic richness and syntactic flexibility of Arabic often lead to multiple interpretations of sentences, introducing ambiguity in generated story endings [18,19]. This ambiguity, exacerbated by the absence of diacritical marks in Modern Standard Arabic (MSA), necessitates contextual clarity to ensure the intended meaning is conveyed.…”

Section: Challenges Due To Arabic Languagementioning

confidence: 99%

Beyond Event-Centric Narratives: Advancing Arabic Story Generation with Large Language Models and Beam Search

Alhussain,

Azmi

2024

Mathematics

View full text Add to dashboard Cite

In the domain of automated story generation, the intricacies of the Arabic language pose distinct challenges. This study introduces a novel methodology that moves away from conventional event-driven narrative frameworks, emphasizing the restructuring of narrative constructs through sophisticated language models. Utilizing mBERT, our approach begins by extracting key story entities. Subsequently, XLM-RoBERTa and a BERT-based linguistic evaluation model are employed to direct beam search algorithms in the replacement of these entities. Further refinement is achieved through Low-Rank Adaptation (LoRA), which fine-tunes the extensive 3 billion-parameter BLOOMZ model specifically for generating Arabic narratives. Our methodology underwent thorough testing and validation, involving individual assessments of each submodel. The ROCStories dataset provided the training ground for our story entity extractor and new entity generator, and was also used in the fine-tuning of the BLOOMZ model. Additionally, the Arabic ComVE dataset was employed to train our commonsense evaluation model. Our extensive analyses yield crucial insights into the efficacy of our approach. The story entity extractor demonstrated robust performance with an F-score of 96.62%. Our commonsense evaluator reported an accuracy of 84.3%, surpassing the previous best by 3.1%. The innovative beam search strategy effectively produced entities that were linguistically and semantically superior to those generated using baseline models. Further subjective evaluations affirm our methodology’s capability to generate high-quality Arabic stories characterized by linguistic fluency and logical coherence.

show abstract

“…Sistem ini diuji pada 300 kalimat dengan kompleksitas yang bervariasi dari buku teks tata bahasa Arab yang digunakan di sekolah. Sistem ini mencapai akurasi keseluruhan sebesar 88,33% (Mannaa et al, 2022). Peneliti mencoba memahami dan memperoleh informasi tambahan yang mungkin muncul dari respon dari pertanyaan yang diberikan saat wawancara terkait pembelajaran e-learning bahasa Arab interaktif.…”

Section: Pembahasanunclassified

Penggunaan Aplikasi E-Learning “HATI” dalam Pembelajaran Bahasa Arab di Perguruan Tinggi Keagamaan Islam Negeri

Hamid

Ifawati

Charis

et al. 2023

AJAS

View full text Add to dashboard Cite

Arabic learning at the State Islamic Religious Universities has not used many applications. This is due to the unavailability of the proper application. The Arabic learning application "HATI" can contribute to learning Arabic. The purpose of this study is to describe the use of the "HATI" application from the perspective of PTKIN students. The research method used is descriptive quantitative using a questionnaire instrument. This study's results indicate that using the HATI application in learning Arabic at PTKIN is very easy and interesting. This is proven that 26.25% of respondents answered that it was effortless to operate the HATI application, 42.43% of respondents answered that it was easy, 22.06% of respondents answered that it was not easy, and 8.97% of respondents said it was not very easy. While 37.87% of respondents answered very interesting, 48.16% answered interesting, 8.82% answered less attractive, and 4.96% answered very unattractive.

show abstract

Computer-assisted i‘raab of Arabic sentences for teaching grammar to students

Cited by 5 publications

References 13 publications

Arabic natural language processing for Qur’anic research: a systematic review

Arabic natural language processing for Qur’anic research: a systematic review

Beyond Event-Centric Narratives: Advancing Arabic Story Generation with Large Language Models and Beam Search

Penggunaan Aplikasi E-Learning “HATI” dalam Pembelajaran Bahasa Arab di Perguruan Tinggi Keagamaan Islam Negeri

Contact Info

Product

Resources

About