Semantic Abductive Network Construction for the Holy Qur’an: A Hybrid Ontology-Based Approach

نویسندگان

1 دانشگاه تهران

2 دانشگاه شهید بهشتی

doi
10.37264/JIQS.V4I1.8
چکیده

The Engineering and constructing semantic networks constitute one of the foundational technologies in the fields of cognitive processing, natural language processing, the semantic web, and the development of artificial intelligence-based systems. Consequently, expertise in the design, construction, engineering, maintenance, evolution, and optimization of ontologies has played a crucial role in advancing intelligent technologies in recent years, and this trend, particularly in the context of dependable and responsible artificial intelligence, is expected to continue in the coming years. The Holy Qur’an, as the sacred book of Muslims worldwide and the primary source of Islamic religion, civilization, and culture, has consistently served as a principal resource in the humanities and Islamic studies, as well as in socio-religious service applications, within Muslim communities. In this paper, a semantic network is automatically constructed using a hybrid approach that integrates multiple technological solutions, including ontologies, word embeddings, co-occurrence analysis, and Arabic root extraction. After the construction of the semantic network and through the application of clustering techniques, several semantic frames were automatically extracted and designated as “abduction frames.” To evaluate the proposed approach, a questionnaire-based assessment was conducted, in which 1,295 individuals participated voluntarily. The results yielded a precision of 69.47% and a recall of 85.35%. Additionally, a mixed quantitative–qualitative evaluation conducted by a panel of experts rated the validity and innovation of the proposed method’s outputs as “good.”

کلیدواژه‌ها
IrGo: A general ontology of Iranian traditional medicine based onMakhzan al-Adwiyah. This ontology includes 3, 521 classes, 15 properties, and 20, 903 axioms (Naghizadeh et al. 2021)., PMD: An ontology of diseases in Persian medicine, designed to classify diseases in traditional Persian medicine. This ontology contains 529 classes and 41 properties (Persian Medicine Diseases Ontology 2019)., QuranJooy: Developed by the Iran Telecommunication Research Center, this ontology includes more than 69, 000 concepts and 8, 000 instances (Mirarab & Khorram 2022)., Borhan: This ontology focuses on Islamic Fiqh (jurisprudence) principles and includes more than 6, 000 classes and 2, 000 relations (Mirarab & Khorram 2022)., FarsNet: In addition to these domain-specific ontologies, FarsNet has been developed as a general-purpose ontology, containing over 100, 000 entries (Shamsfard et al. 2009)., Identifying final words using TF-IDF thresholding, Identifying final words using a thesaurus, Identifying final words using normalization, word embedding, and FarsNet, FarsNet covers more than one million nodes (words)., It is general-purpose., It was manually produced (non-automatically), thus having very high reliability. Additionally, it is continuously updated with the help of crowd-sourcing., It provides a suitable application programming interface (API), available both online and offline., It has been practically evaluated in various applications and is recognized as a key technical infrastructure for Persian NLP., Identifying pairs of verses that share more than 3 common roots. If a pair of verses shares fewer than 3 common roots, they are considered unrelated., Calculating the RR relation (Root Relation): For all common roots in each verse pair., Calculation of TRR for all words:, The word exists in the AminMozhgani or FarsiYar word embedding models., Co-occurrences of the word are present in FarsNet., Low informativeness of the word (absence from FarsNet or word embedding models)., Low connectivity of the word (very low scores, near zero, with other words)., A word is randomly selected from the cluster-related words (true positive) and becomes the query word. The ideal response here is "very high.", A word is selected from unrelated words (true negative) and becomes the query word. The ideal response here is "very low"., True Positive (TP): The model agrees with human judgment, both indicating high word belonging., True Negative (TN): The model agrees with human judgment, both indicating low word belonging., False Positive (FP): The model indicates high belonging contrary to human low assessment., False Negative (FN): The model indicates low belonging contrary to human high assessment., To what extent are these concepts semantically related or associated? This question had 5 options: very high, high, medium, low, very low. Very high was scored as 5, and very low as 1., If the computational Qur’an mining detects associations between these concepts, does it identify innovative connections (from a research perspective) among some concepts? This question had 4 options:, Yes, the connection is highly innovative research-wise., Yes, the connection is innovative research-wise., No, it is relatively established in prior research., No, the connection is entirely obvious and well-known., RIS, EndNote, Mendeley, BibTeX, APA, MLA, HARVARD, CHICAGO, VANCOUVER