Non-taxonomic Relations Research Articles

LLMs4OL 2024 Datasets: Toward Ontology Learning with Large Language Models

Ontology learning (OL) from unstructured data has evolved significantly, with recent advancements integrating large language models (LLMs) to enhance various aspects of the process. The paper introduces the LLMs4OL 2024 datasets, developed to benchmark and advance research in OL using LLMs. The LLMs4OL 2024 dataset as a key component of the LLMs4OL Challenge, targets three primary OL tasks: Term Typing, Taxonomy Discovery, and Non-Taxonomic Relation Extraction. It encompasses seven domains, i.e. lexosemantics and biological functions, offering a comprehensive resource for evaluating LLM-based OL approaches Each task within the dataset is carefully crafted to facilitate both Few-Shot (FS) and Zero-Shot (ZS) evaluation scenarios, allowing for robust assessment of model performance across different knowledge domains to address a critical gap in the field by offering standardized benchmarks for fair comparison for evaluating LLM applications in OL.

Preface for LLMs4OL 2024: The 1st Large Language Models for Ontology Learning Challenge at the 23rd ISWC

We are pleased to present the proceedings of the “1st Large Language Models for Ontology Learning Challenge (LLMs4OL 2024)”, held at the 23rd International Semantic Web Conference (ISWC). This challenge marks a significant a dvancement in utilizing Large Language Models (LLMs) for Ontology Learning (OL)—a key Semantic Web component that facilitates the automatic extraction of structured knowledge from unstructured data. The challenge features three main tasks: Term Typing (identifying categories for terms), Taxonomy Discovery (uncovering hierarchical relationships), and Non-Taxonomic Relation Extraction (identifying other meaningful relationships between terms). Each task is designed to test different facets of ontology construction and to encourage the exploration of innovative techniques. This challenge seeks to foster collaboration, inspire innovation, and expand the capabilities of LLMs in OL. The proceedings include a collection of innovative solutions and insights from global participants, highlighting the crucial role of LLMs in enhancing the web with structured knowledge. We believe the outcomes of this challenge will propel further advancements in OL and its applications on the semantic web. We would like to extend our gratitude to all the participants for their invaluable contributions, which their solutions and dedication have greatly enriched this challenge. Our sincere thanks also go to the conference organizers and committee for their efforts in hosting this event. We are deeply appreciative of the reviewers for their evaluations and feedback. Their reviews have been instrumental in enhancing the quality of the submissions. We would like to specifically acknowledge: Dr. Amin Keshavarzi (Postdoctoral Researcher, L3S & TIB, Germany) Mostafa Rahgouy (Lead Project Coordinator, Auburn University, USA) Sahar Tahmasebi (Doctoral Researcher, TIB, Germany) Milad Molazadeh Oskuee (Lead NLP Researcher, Iran) Aida Usmanova (Doctoral Researcher, Leuphana Universit ¨ at L¨uneburg, Germany) Emetis Niazmand (Doctoral Researcher, TIB, Germany) Lastly, we would like to express our gratitude to ”Xenia Felice van Edig” and ”Karolina Linerová” from the TIB Open Publishing, for their support in bringing these proceedings online. We also would like to acknowledge that the 1st LLMs4OL Challenge @ ISWC 2024 jointly supported by the NFDI4DataScience initiative (DFG, German Research Foundation, Grant ID: 460234259) and the SCINEXT project (BMBF, German Federal Ministry of Education and Research, Grant ID: 01lS22070).

The Ghost at LLMs4OL 2024 Task A: Prompt-Tuning-Based Large Language Models for Term Typing

The LLMs4OL Challenge @ ISWC 2024 aims to explore the intersection of Large Language Models (LLMs) and Ontology Learning (OL) through three main tasks: 1) Term Typing, 2) Taxonomy Discovery and 3) Non-Taxonomic Relation Extraction. In this paper, we present our system's design for the term typing task. Our approach utilizes automatic prompt generation using soft prompts to enhance term typing accuracy and efficiency. We conducted experiments on several datasets, including WordNet, UMLS, GeoNames, NCI, MEDCIN, and SNOMEDCT_US. Our approach outperformed the baselines on most datasets, except for GeoNames, where it faced challenges due to the complexity and specificity of this domain, resulting in substantially lower scores. Additionally, we report the overall results of our approach in this challenge, which highlight its promise while also indicating areas for further improvement.

Evaluating semantic similarity and relatedness between concepts by combining taxonomic and non-taxonomic semantic features of WordNet and Wikipedia

Many applications in cognitive science and artificial intelligence utilize semantic similarity and relatedness to solve difficult tasks such as information retrieval, word sense disambiguation, and text classification. Previously, several approaches for evaluating concept similarity and relatedness based on WordNet or Wikipedia have been proposed. WordNet-based methods rely on highly precise knowledge but have limited lexical coverage. In contrast, Wikipedia-based models achieve more coverage but sacrifice knowledge quality. Therefore, in this paper, we focus on developing a comprehensive semantic similarity and relatedness method based on WordNet and Wikipedia. To improve the accuracy of existing measures, we combine various taxonomic and non-taxonomic features of WordNet, including gloss, lemmas, examples, sister-terms, derivations, holonyms/meronyms, and hypernyms/hyponyms, with Wikipedia gloss and hyperlinks, to describe concepts. We present a novel technique for extracting ‘is-a’ and ‘part-whole’ relationships between concepts using the Wikipedia link structure. The suggested technique identifies taxonomic and non-taxonomic relationships between concepts and offers dense vector representations of concepts. To fully exploit WordNet and Wikipedia’s semantic attributes, the proposed method integrates their semantic knowledge at feature-level, combining semantic similarity and relatedness into a single comprehensive measure. The experimental results demonstrate the effectiveness of the proposed method over state-of-the-art measures on various gold standard benchmarks.

Weighted graph convolution over dependency trees for nontaxonomic relation extraction on public opinion information

Weighted graph convolution over dependency trees for nontaxonomic relation extraction on public opinion information

Learning Non-Taxonomic Relations of Ontologies

Ontologies, as semantic knowledge representation, have a crucial role in various information systems. The main pitfall of manually building ontologies is effort and time-consuming. Ontology learning is a key solution. Learning Non-Taxonomic Relationships of Ontologies (LNTRO) is the process of automatic/semi-automatic extraction of all possible relationships between concepts in a specific domain, except the hierarchal relations. Most of the research works focused on the extraction of concepts and taxonomic relations in the ontology learning process. This article presents the results of a systematic review of the state-of-the-art approaches for LNTRO. Sixteen approaches have been described and qualitatively analyzed. The solutions they provide are discussed along with their respective positive and negative aspects. The goal is to provide researchers in this area a comprehensive understanding of the drawbacks of the existing work, thereby encouraging further improvement of the research work in this area. Furthermore, this article proposes a set of recommendations for future research.

Exploiting non-taxonomic relations for measuring semantic similarity and relatedness in WordNet

Various applications in computational linguistics and artificial intelligence employ semantic similarity to solve challenging tasks, such as word sense disambiguation, text classification, information retrieval, machine translation, and document clustering. To our knowledge, research to date rely solely on the taxonomic relation “ISA” to evaluate semantic similarity and relatedness between terms. This paper explores the benefits of using all types of non-taxonomic relations in large linked data, such as WordNet knowledge graph, to enhance existing semantic similarity and relatedness measures. We propose a holistic poly-relational approach based on a new relation-based information content and non-taxonomic-based weighted paths to devise a comprehensive semantic similarity and relatedness measure. To demonstrate the benefits of exploiting non-taxonomic relations in a knowledge graph, we used three strategies to deploy non-taxonomic relations at different granularity levels. We conduct experiments on four well-known gold standard datasets. The results of our proposed method demonstrate an improvement over the benchmark semantic similarity methods, including the state-of-the-art knowledge graph embedding techniques, that ranged from 3.8%–23.8%, 1.3%–18.3%, 31.8%–117.2%, and 19.1%–111.1%, on all gold standard datasets MC, RG, WordSim, and Mturk, respectively. These results demonstrate the robustness and scalability of the proposed semantic similarity and relatedness measure, significantly improving existing similarity measures.

STRUCTURAL ANALYSIS OF SEMANTIC RELATIONS REGARDING INTEGRATION AND ASSOCIATION OF SEMANTIC NETWORK IN VOCBENCH AS AN AGRICULTURAL ONTOLOGY

The purpose of this article is to analyze semantic relations based on graph-independent structural analysis in VocBench. The mix-method of deductive and inductive approach is adapted in operating the research methodology, especially for data collection. The research data are structural domains of semantic relations in ontologies. The data resource is the authoritative agricultural ontology, VocBench, that has been originated by Food and Agricultural organization (FAO), United Nation. VocBench includes around 40000 concepts. The sample size is around 1500 concepts. Sampling technique used is the stratified random sampling. The data analysis results are employed in the SPSS and Excel software using descriptive and proportional analysis. The research results reveal that the taxonomic relations cover a wide area in VocBench. Moreover, the overloading was not seen in the usage of non-taxonomic relations. The high frequency in the usage of the semantic relations’ output might be implied the possibility of the width (i.e., exhaustivity) in semantic network in VocBench.

Neo-Davidsonian-Based Event Class Semantic Representation

Abstract Event class is an abstract event that represents a set of events with some common features. There are inherent relations among event classes. Event classes and their relations are the important parts of event knowledge base. We gave a novel framework to represent event class semantic by marriage Neo-Davidsonian event semantic and 6-element event class model. The framework treated the predicate of event class as unary predicate with event class argument ec only. It connected the predicate and the other elements of event class with connecting symbol ⁁. And the framework can’t only represent the taxonomic relations among event classes, but also respectively represent non-taxonomic relations via the connecting symbols ⊄, ⊳, →, ∥ and ⊒. The representation examples indicate the novel framework can represent event classes semantic and different kinds of relations among event classes.

Towards relation extraction from Arabic text: a review

Semantic relation extraction is an important component of ontologies that can support many applications e.g. text mining, question answering, and information extraction. However, extracting semantic relations between concepts is not trivial and one of the main challenges in Natural Language Processing (NLP) Field. The Arabic language has complex morphological, grammatical, and semantic aspects since it is a highly inflectional and derivational language, which makes task even more challenging. In this paper, we present a review of the state of the art for relation extraction from texts, addressing the progress and difficulties in this field. We discuss several aspects related to this task, considering the taxonomic and non-taxonomic relation extraction methods. Majority of relation extraction approaches implement a combination of statistical and linguistic techniques to extract semantic relations from text. We also give special attention to the state of the work on relation extraction from Arabic texts, which need further progress.

Decoding Chinese User Generated Categories for Fine-Grained Knowledge Harvesting

User Generated Categories (UGCs) are short but informative phrases that reflect how people describe and organize entities. UGCs express semantic relations among entities implicitly hence serve as a rich data source for knowledge harvesting. However, most UGC relation extraction methods focus on English and heavily rely on lexical and syntactic patterns. Applying them directly to Chinese UGCs poses significant challenges because Chinese is an analytic language with flexible language expressions. In this paper, we aim at harvesting fine-grained relations from Chinese UGCs automatically. Based on neural networks and negative sampling, we introduce two word embedding projection models to identify is-a relations. The accuracy of prediction results is improved via a collective refinement algorithm and a hypernym expansion method. We further propose a graph clique mining algorithm to harvest non-taxonomic relations from UGCs, together with their textual patterns. Two experiments are conducted to validate our approach based on Chinese Wikipedia. The first experiment verifies the is-a relation extraction approach achieves high accuracy, outperforming state-of-the-art methods. The second experiment shows that the proposed method can harvest non-taxonomic relations of large quantity and high accuracy, with minimal human intervention.

Extraction of Concept and Concept Relation for Islamic Term Using Syntactic Pattern Approach

Ontology Learning is a semi automation step to learn ontology from text. The identification of a term become a prerequisite for all aspects of Ontology Learning. The Ontological Learning Layer is started by identifying terms, synonyms, concepts, hierarchical concepts, relationships and rules for various domain text including Islamic-based text or Islamic Glossary. The glossary of Islamic terms translated into English has been in abundance and requires extraction of important information for a clear understanding of an Islamic term. The existence of a list of Islamic terms is to minimize the spelling diversity, to seek the concept of the term and provide guidance for a unique Islamic concept. However, this electronic form provides a serious problem to achieve machine operation. The study aims to identify and extract concepts, taxonomies, relationships and rules that can be built on the domain of the terms in Islamic glossary specific to the field of Islamic Pillars. This extraction involves the use of Hearst pattern approach. The data set used is from the Dictionary or Islamic Glossary of the International Islamic University of Malaysia (DEED 2015). The dictionary consists of Islamic terms, which are the concepts and intentions of each concepts in alphabetical order. The study used six phases involving the preparation, processing and testing phase that are merged with the methodology design of the study. A total of 41 concepts were successfully extracted based on 6 Hearst pattern, 31 manually generated rules from 19 sentences and 9 non-taxonomic relationships. The result of the study concluded that the objective of this study was achieved in the scope determined when the results of the study and testing conducted by the assessors in the domain showed positive results. Research constraints are presented to enable researchers to improve the research from time to time. Research proposals for future research have been described so that this study will be more useful and expanded to the next comprehensive guide of Muslims.

Linked open data-based framework for automatic biomedical ontology generation

BackgroundFulfilling the vision of Semantic Web requires an accurate data model for organizing knowledge and sharing common understanding of the domain. Fitting this description, ontologies are the cornerstones of Semantic Web and can be used to solve many problems of clinical information and biomedical engineering, such as word sense disambiguation, semantic similarity, question answering, ontology alignment, etc. Manual construction of ontology is labor intensive and requires domain experts and ontology engineers. To downsize the labor-intensive nature of ontology generation and minimize the need for domain experts, we present a novel automated ontology generation framework, Linked Open Data approach for Automatic Biomedical Ontology Generation (LOD-ABOG), which is empowered by Linked Open Data (LOD). LOD-ABOG performs concept extraction using knowledge base mainly UMLS and LOD, along with Natural Language Processing (NLP) operations; and applies relation extraction using LOD, Breadth first Search (BSF) graph method, and Freepal repository patterns.ResultsOur evaluation shows improved results in most of the tasks of ontology generation compared to those obtained by existing frameworks. We evaluated the performance of individual tasks (modules) of proposed framework using CDR and SemMedDB datasets. For concept extraction, evaluation shows an average F-measure of 58.12% for CDR corpus and 81.68% for SemMedDB; F-measure of 65.26% and 77.44% for biomedical taxonomic relation extraction using datasets of CDR and SemMedDB, respectively; and F-measure of 52.78% and 58.12% for biomedical non-taxonomic relation extraction using CDR corpus and SemMedDB, respectively. Additionally, the comparison with manually constructed baseline Alzheimer ontology shows F-measure of 72.48% in terms of concepts detection, 76.27% in relation extraction, and 83.28% in property extraction. Also, we compared our proposed framework with ontology-learning framework called “OntoGain” which shows that LOD-ABOG performs 14.76% better in terms of relation extraction.ConclusionThis paper has presented LOD-ABOG framework which shows that current LOD sources and technologies are a promising solution to automate the process of biomedical ontology generation and extract relations to a greater extent. In addition, unlike existing frameworks which require domain experts in ontology development process, the proposed approach requires involvement of them only for improvement purpose at the end of ontology life cycle.

Automated ontology generation framework powered by linked biomedical ontologies for disease-drug domain

Objective and background: The exponential growth of the unstructured data available in biomedical literature, and Electronic Health Record (EHR), requires powerful novel technologies and architectures to unlock the information hidden in the unstructured data. The success of smart healthcare applications such as clinical decision support systems, disease diagnosis systems, and healthcare management systems depends on knowledge that is understandable by machines to interpret and infer new knowledge from it. In this regard, ontological data models are expected to play a vital role to organize, integrate, and make informative inferences with the knowledge implicit in that unstructured data and represent the resultant knowledge in a form that machines can understand. However, constructing such models is challenging because they demand intensive labor, domain experts, and ontology engineers. Such requirements impose a limit on the scale or scope of ontological data models. We present a framework that will allow mitigating the time-intensity to build ontologies and achieve machine interoperability.Methods: Empowered by linked biomedical ontologies, our proposed novel Automated Ontology Generation Framework consists of five major modules: a) Text Processing using compute on demand approach. b) Medical Semantic Annotation using N-Gram, ontology linking and classification algorithms, c) Relation Extraction using graph method and Syntactic Patterns, d), Semantic Enrichment using RDF mining, e) Domain Inference Engine to build the formal ontology.Results: Quantitative evaluations show 84.78% recall, 53.35% precision, and 67.70% F-measure in terms of disease-drug concepts identification; 85.51% recall, 69.61% precision, and F-measure 76.74% with respect to taxonomic relation extraction; and 77.20% recall, 40.10% precision, and F-measure 52.78% with respect to biomedical non-taxonomic relation extraction.Conclusion: We present an automated ontology generation framework that is empowered by Linked Biomedical Ontologies. This framework integrates various natural language processing, semantic enrichment, syntactic pattern, and graph algorithm based techniques. Moreover, it shows that using Linked Biomedical Ontologies enables a promising solution to the problem of automating the process of disease-drug ontology generation.

Developing a domain ontology for knowledge management technologies

PurposeThe purpose of this paper is to develop a new ontology for knowledge management (KM) technologies, determining the relationships between these technologies and classification of them.Design/methodology/approachThe study applies NOY methodology – named after Natalya F. Noy who initiated this methodology. Protégé software and ontology web language are used for building the ontology. The presented ontology is evaluated with abbreviation and consistency criteria and knowledge retrieval of KM technologies by experts.FindingsAll the main concepts in the scope of KM technologies are extracted from existing literature. There are 241 words, 49 out of them are domain concepts, eight terms are about taxonomic and non-taxonomic relations, one term relates to data property and 183 terms are instances. These terms are used to develop KM technologies’ ontology based on three factors: facilitating KM processes, supporting KM strategies and the position of technology in the KM technology stage model. The presented ontology is created a common understanding in the field of KM technologies.Research limitations/implicationsLack of specific documentary about logic behind decision making and prioritizing criteria in choosing KM technologies.Practical implicationsUploading the presented ontology in the web environment provides a platform for knowledge sharing between experts from around the world. In addition, it helps to decide on the choice of KM technologies based on KM processes and KM strategy.Originality/valueAmong the many categories of KM technologies in literature, there is no classifying according to several criteria simultaneously. This paper contributes to filling this gap and considers KM processes, KM strategy and stages of growth for KM technologies simultaneously to choice the KM technologies and also there exists no formal ontology regarding KM technologies. This study has tried to propose a formal KM technologies’ ontology.

Automatic Non-Taxonomic Relation Extraction from Big Data in Smart City

The explosive data growth in smart city is making domain big data a hot topic for knowledge extraction. Non-taxonomic relations refer to any relations between concept pairs except the is-a relation, which is an important part of Knowledge Graph. In this paper, toward big data in smart city, we present a multi-phase correlation search framework to automatically extract non-taxonomic relations from domain documents. Different kinds of semantic information are used to improve the performance of the system. First, inspired by the works of network representation; we propose a Semantic Graph-Based method to combine structure information of semantic graph and context information of terms together for non-taxonomic relationships identification. Second, different semantic types of verb sets are extracted based on the dependency syntactic information, which are ranked to act as non-taxonomic relationship labels. Extensive experiments demonstrate the efficiency of the proposed framework. The F1 value reaches 81.4% for identification of non-taxonomic relationships. The total precision of the non-taxonomic relationship labels extraction is 73.4%, and 87.8% non-taxonomic relations can be provided with “good” labels. We hope this article can provide a useful way for domain big data knowledge extraction in smart city.

Joint learning of ontology and semantic parser from text

Semantic parsing methods are used for capturing and representing semantic meaning of text. Meaning representation capturing all the concepts in the text may not always be available or may not be sufficiently complete. Ontologies provide a structured and reasoning-capable way to model the content of a collection of texts. In this work, we present a novel approach to joint learning of ontology and semantic parser from text. The method is based on semi-automatic induction of a context-free grammar from semantically annotated text. The grammar parses the text into semantic trees. Both, the grammar and the semantic trees are used to learn the ontology on several levels -- classes, instances, taxonomic and non-taxonomic relations. The approach was evaluated on the first sentences of Wikipedia pages describing people.

Ontological based Relevance Abstraction Identification Technique and Evaluation

Background/Objectives: To develop ontology based relevance abstraction identification technique for efficient Abstract identification. Methods/Statistical Analysis: The abstract terms are extracted from software related documents such as software requirement specifications, compilation report, bug corpus report, library code documents, testing materials and so on. Abstract identification is the process of analysing and identifying the important key words that are present in the requirements document which is essential to understood requirements for better development process. Findings: The automated abstraction identification was proposed to extract abstract terms called relevance-based abstraction identification (RAI). RAI-0 and RAI-1 two versions of abstraction identification were proposed. In RAI-1 significance score of term is calculated by assigning variable weights for terms based on the likelihood values where as RAI-0 assign equal weight for all terms. The main issues in RAI is used the lexical similarity which has to improved by using work Ontological based relevance Abstraction Identification (O-RAI) with consideration of conceptual meaning words. This work aims to retrieve the abstract terms by finding the conceptual meaning of every terms present in the requirements document. The O-RAI is implemented by constructing the domain ontology in the automated manner by using the methodology called the episode based ontology construction mechanism.An episode is a partially ordered collection of actions taking place together which is represented as directed acyclic graphs. In episode based ontology construction mechanism, concept attributes and relation among attributes are extracted from episodes, the non-taxonomic relations among attribute also formed based on episodes. Improvements/Applications: The significant score of relevant terms from documents is calculated with considering the conceptual of terms which are occurred in the domain ontology. Thus semantic significant score is used to rank the relevance abstract terms.

Semantic Network Formalism for Knowledge Representation

In this paper, the authors propose formalism for representing a knowledge base (KB) by network. The objective is to achieve a high coverage of this base. This type of network is similar to the semantic network with the difference that the arcs are quantified by a value indicating the semantic proximity between the concepts. This semantic proximity presents taxonomic relations, synonyms, and non-taxonomic relations (contextual relations). This latter are discovered based on the association rules model. This model is based on (i) indexing method (ii) the French lexical database EuroWordNet (EWNF) and (iii) the Apriori algorithm. The contextual relations are the latent relations buried in the KB, carried by the semantic context. Evaluating our representation formalism shows better result about 80% of coverage of the KB.

An Automatic and Clause-Based Approach to Learn Relations for Ontologies

Ontology learning from text is one of the knowledge acquisition processes that facilitates construction of ontology. Considerable research is being done on learning concepts and relations, especially on acquiring semantic relations between concepts for a specific domain. However, more of the research contributions are in learning either taxonomic relations or semantic relations but not in both. Even those few research works that address learning of both types of relations deal with simple sentences only resulting in low recall value. Further, these approaches are semi-automatic, which require either user's feedback or domain expert's knowledge. In this paper, we propose a single framework that is automatic and domain-independent that helps in learning both taxonomic and non-taxonomic relations. We have developed a clause-based approach that automatically extracts the relations for concepts from unstructured text documents. Our approach is capable of handling complex sentences by identifying hidden triples present in the sentences. We have evaluated our methodology of relation learning for the concepts specified by AGROVOC and Open Directory Project using a corpus of web documents. The precision, recall and F1-measure of our method were observed to be considerably higher than those of state-of-the-art methodologies for relation learning.