Ontology-Based Semantic Normalization of Resumes for Classification

LLM-Assisted Ontology Engineering and Construction of a French Legal Knowledge Graph

Maintenance regulations are complex legal texts that are difficult to exploit when addressing a specific case and challenging to integrate into operational systems. This paper presents a two-stage LLM-assisted workflow for French maintenance regulations: ontology engineering from a SEMLEG-based core ontology, followed by construction of an ontology-grounded French legal knowledge graph. The first stage consists in the open extraction of typed entities and triples from a stratified corpus sample, the normalization of labels through embedding-based fusion, and the induction of candidate object properties with their signature (domain and range). The second stage uses the resulting ontology to guide the closed extraction of triples and RDF graph construction over the full corpus. Experiments with GPT-4.1 and mistral-large-2512 show robust structured outputs, near-complete class alignment, and a substantial reduction of duplicated entities and predicates after fusion. Fewer than 20% of triples introduce unseen properties, while lower exact signature compliance reveals new domain-range combinations for existing predicates. These results point to predicate normalization and the validation of newly observed relation signatures as key refinement steps for industrial maintenance settings.

Ontology-Based Text Summarization for Marathi Legal Documents

Objectives/Background: Government documents of Maharashtra state are written in Marathi language, and they are long in length, detailed, and difficult to read quickly. There is a requirement to develop a system which will automatically summarize these documents to understand the key information quickly. Therefore, this research aims to create an ontology-based method for summarizing government documents by improving understanding using domain-specific terms and their relationships. Method: This study proposes a novel technique that uses ontology as a knowledge base, which consists of significant concepts associated with a specific subject and their interconnections. It helps the system to understand the content with its meaning. With this understanding, the algorithm selects important information and generates summaries that maintain the clarity and importance of the text. Findings: The proposed method achieves Precision of 0.82, ROUGE-1 score of 0.85, and ROUGE-2 score of 0.78. These results show that the summaries are accurate, meaningful and match the reference summaries. The proposed system may also reduce the effort required to read long documents by generating short and meaningful summaries. It improves both the quality and reliability of text summarization and works well for domain-specific applications where meaningful summaries are important. Novelty: This research work is different from the traditional statistical text summarization techniques as it uses the ontology to capture text relationships resulting in an improved context understanding and accurate summaries. Keywords: Text Summarization, Ontology-based, Domain knowledge, Marathi Language, Administrative documents

Hybrid LLM and Embedding Ontology Matching with Reference Ontologies

Authors’ responses to the feedback of the reviewers Paper: From Manual to LLM-assisted: A Mapping Review on Ontology Construction Methods

Computational Tool for Automatic Term Extraction - ATEM

Automatic term extraction enables the identification of the most representative terms within a corpus through computational processes. This process facilitates the creation of lexicographic materials or common databases, which are pivotal for knowledge acquisition in science as they help eliminate ambiguity in definitions pertaining to a specific domain. Specialized literature highlights the need for a common foundation on best practices for the Internet of Things (IoT) to consolidate knowledge and adapt new working methods. However, the manual creation of terminological resources is inefficient, does not keep pace with the rapid evolution of subjects, and is both time-consuming and costly. This article introduces ATEM, a term extraction tool for web and mobile environments that incorporates a hybrid method for identifying relevant terms in English-language scientific literature on IoT. ATEM is developed using a Service-Oriented Architecture (SOA) and employs programming languages such as JavaScript and Python. It also uses tools like the Flask framework and NLP-specific libraries such as NLTK and SpaCy. The computational tool includes the CValue algorithm, along with statistical and linguistic techniques in several steps: (i) corpus reception; (ii) text preprocessing; (iii) stop-word removal; (iv) Part-of-Speech (POS) tagging; and (v) filtering through linguistic and statistical rules. This results in a list of potential terms and a weight indicating their relevance within the corpus. The method was tested on five corpora from different domains, and ATEM processes and retrieves terms with 75% precision and 89% recall, highlighting its versatility across corpora. According to the tests, ATEM supports terminological extraction from IoT literature. It contributes to: (i) the development of lexicographic resources; (ii) language translation; and (iii) the creation of shared databases.

Semantic Intelligence Against CSAM: The PreventCSA@EU Ontology Framework for Classification and Investigation

This work presents the PreventCSA@EU ontology, a semantically grounded framework designed to support the identification, classification, annotation, and analysis of online Child Sexual Abuse and Child Sexual Exploitation Material (CSAM/CSEM). The growing circulation and dissemination of CSAM/CSEM across digital environments, combined with inconsistencies in legal definitions and classification practices across jurisdictions, highlights the need for semantically interoperable frameworks capable of supporting cross-organizational cooperation and automated processing. The proposed ontology is developed through a systematic review and comparative analysis of existing CSA/CSE-related, metadata oriented, and investigative ontologies and taxonomies, with its primary design aimed at addressing the operational needs and domain-specific requirements of national LEA Directorates. It introduces a hierarchical semantic model built around core entities such as Media Object, Content, Person, Depiction, and Investigative Report, while enabling structured alignment with INHOPE UCS labels, Dublin Core-DMCI Metadata Terms, and Schema.org. The proposed framework emphasizes ontology-driven interoperability for structured annotation and analysis of CSA/CSE-related data, supporting consistent classification, child identification, and investigative processes for offender prosecution. The design aims extend existing classification approaches with additional conceptual structures for database conceptualization, process modeling, and ontology-driven data management. By integrating established classification standards with a novel hierarchical ontology, the proposed framework enhances cross-system compatibility, with particular relevance to emerging EU-level data infrastructures, including the envisaged EU Center database under the proposed Child Sexual Abuse Regulation (CSAR).