Kerry Taylor

Shuaiqun Pan, Sergio J. Rodríguez Méndez, Kerry Taylor

Data mining techniques can transform massive amounts of unstructured data into quantitative data that quickly reveal insights, trends, and patterns behind the original data. In this paper, a data mining model is applied to analyse the 2019 grant applications submitted to an Australian Government research funding agency to investigate whether grant schemes successfully identifies innovative project proposals, as intended. The grant applications are peer-reviewed research proposals that include specific ``innovation and creativity'' (IC) scores assigned by reviewers. In addition to predicting the IC score for each research proposal, we are particularly interested in understanding the vocabulary of innovative proposals. In order to solve this problem, various data mining models and feature encoding algorithms are studied and explored. As a result, we propose a model with the best performance, a Random Forest (RF) classifier over documents encoded with features denoting the presence or absence of unigrams. In specific, the unigram terms are encoded by a modified Term Frequency - Inverse Document Frequency (TF-IDF) algorithm, which only implements the IDF part of TF-IDF. Besides the proposed model, this paper also presents a rigorous experimental pipeline for analysing grant applications, and the experimental results prove its feasibility.

Zhangcheng Qiang, Stuart Hands, Kerry Taylor et al.

Ontologies play a critical role in data exchange, information integration, and knowledge sharing across diverse smart building applications. Yet, semantic differences between the prevailing building ontologies hamper their purpose of bringing data interoperability and restrict the ability to reuse building ontologies in real-world applications. In this paper, we propose and adopt a framework to conduct a systematic comparison and evaluation of four popular building ontologies (Brick Schema, RealEstateCore, Project Haystack and Google's Digital Buildings) from both axiomatic design and assertions in a use case, namely the Terminological Box (TBox) evaluation and the Assertion Box (ABox) evaluation. In the TBox evaluation, we use the SQuaRE-based Ontology Quality Evaluation (OQuaRE) Framework and concede that Project Haystack and Brick Schema are more compact with respect to the ontology axiomatic design. In the ABox evaluation, we apply an empirical study with sample building data that suggests that Brick Schema and RealEstateCore have greater completeness and expressiveness in capturing the main concepts and relations within the building domain. The results implicitly indicate that there is no universal building ontology for integrating Linked Building Data (LBD). We also discuss ontology compatibility and investigate building ontology design patterns (ODPs) to support ontology matching, alignment, and harmonisation.

Zhangcheng Qiang, Kerry Taylor, Weiqing Wang

The classical text preprocessing pipeline, comprising Tokenisation, Normalisation, Stop Words Removal, and Stemming/Lemmatisation, has been implemented in many systems for ontology matching (OM). However, the lack of standardisation in text preprocessing creates diversity in the mapping results. In this paper, we investigate the effect of the text preprocessing pipeline on 8 Ontology Alignment Evaluation Initiative (OAEI) tracks with 49 distinct alignments. We find that Tokenisation and Normalisation (categorised as Phase 1 text preprocessing) are more effective than Stop Words Removal and Stemming/Lemmatisation (categorised as Phase 2 text preprocessing). We propose two novel approaches to repair unwanted false mappings that occur in Phase 2 text preprocessing. One is a pre hoc logic-based repair approach used before text preprocessing, employing an ontology-specific check to find common words that cause false mappings. The other repair approach is the post hoc large language model (LLM)-based approach, used after text preprocessing, which utilises the strong background knowledge provided by LLMs to repair non-existent and counter-intuitive false mappings. The experimental results indicate that these two approaches can significantly improve the matching correctness and the overall matching performance.

Zhangcheng Qiang, Kerry Taylor, Weiqing Wang et al.

Hallucinations of large language models (LLMs) commonly occur in domain-specific downstream tasks, with no exception in ontology matching (OM). The prevalence of using LLMs for OM raises the need for benchmarks to better understand LLM hallucinations. The OAEI-LLM dataset is an extended version of the Ontology Alignment Evaluation Initiative (OAEI) datasets that evaluate LLM-specific hallucinations in OM tasks. We outline the methodology used in dataset construction and schema extension, and provide examples of potential use cases.

Zhangcheng Qiang, Kerry Taylor, Weiqing Wang

Due to the dynamic nature of the Semantic Web, version control is necessary to manage changes in widely used ontologies. Despite the long-standing recognition of ontology versioning (OV) as a crucial component of efficient ontology management, many approaches treat OV as similar to ontology matching (OM) and directly reuse OM systems for OV tasks. In this study, we systematically analyse similarities and differences between OM and OV and formalise an OM4OV pipeline to offer more advanced OV support. The pipeline is implemented and evaluated in the state-of-the-art OM system Agent-OM. The experimental results indicate that OM systems can be effectively reused for OV tasks, but without necessary extensions, can produce skewed measurements, poor performance in detecting update entities, and limited explanation of false mappings. To tackle these issues, we propose an optimisation method called the cross-reference (CR) mechanism, which builds on existing OM alignments to reduce the number of matching candidates and to improve overall OV performance.

Zhangcheng Qiang, Kerry Taylor, Weiqing Wang

Due to the dynamic nature of the Semantic Web, version control is necessary to manage changes in widely used ontologies. Despite the long-standing recognition of ontology versioning (OV) as a crucial component of efficient ontology management, many approaches treat OV as similar to ontology matching (OM) and directly reuse OM systems for OV tasks. In this study, we systematically analyse similarities and differences between OM and OV and formalise an OM4OV pipeline to offer more advanced OV support. The pipeline is implemented and evaluated in the state-of-the-art OM system Agent-OM. The experimental results indicate that OM systems can be effectively reused for OV tasks, but without necessary extensions, can produce skewed measurements, poor performance in detecting update entities, and limited explanation of false mappings. To tackle these issues, we propose an optimisation method called the cross-reference (CR) mechanism, which builds on existing OM alignments to reduce the number of matching candidates and to improve overall OV performance.

Nathan Elazar, Kerry Taylor

We investigate the feasibility of using mixtures of interpretable experts (MoIE) to build interpretable image classifiers on MNIST10. MoIE uses a black-box router to assign each input to one of many inherently interpretable experts, thereby providing insight into why a particular classification decision was made. We find that a naively trained MoIE will learn to 'cheat', whereby the black-box router will solve the classification problem by itself, with each expert simply learning a constant function for one particular class. We propose to solve this problem by introducing interpretable routers and training the black-box router's decisions to match the interpretable router. In addition, we propose a novel implicit parameterization scheme that allows us to build mixtures of arbitrary numbers of experts, allowing us to study how classification performance, local and global interpretability vary as the number of experts is increased. Our new model, dubbed Implicit Mixture of Interpretable Experts (IMoIE) can match state-of-the-art classification accuracy on MNIST10 while providing local interpretability, and can provide global interpretability albeit at the cost of reduced classification accuracy.

Zhangcheng Qiang, Kerry Taylor, Weiqing Wang et al.

Hallucinations are often inevitable in downstream tasks using large language models (LLMs). To tackle the substantial challenge of addressing hallucinations for LLM-based ontology matching (OM) systems, we introduce a new benchmark dataset OAEI-LLM-T. The dataset evolves from seven TBox datasets in the Ontology Alignment Evaluation Initiative (OAEI), capturing hallucinations of ten different LLMs performing OM tasks. These OM-specific hallucinations are organised into two primary categories and six sub-categories. We showcase the usefulness of the dataset in constructing an LLM leaderboard for OM tasks and for fine-tuning LLMs used in OM tasks.

Zhangcheng Qiang, Kerry Taylor, Weiqing Wang

The classical text preprocessing pipeline, comprising Tokenisation, Normalisation, Stop Words Removal, and Stemming/Lemmatisation, has been implemented in many systems for ontology matching (OM). However, the lack of standardisation in text preprocessing creates diversity in the mapping results. In this paper, we investigate the effect of the text preprocessing pipeline on 8 Ontology Alignment Evaluation Initiative (OAEI) tracks with 49 distinct alignments. We find that Tokenisation and Normalisation (categorised as Phase 1 text preprocessing) are more effective than Stop Words Removal and Stemming/Lemmatisation (categorised as Phase 2 text preprocessing). We propose two novel approaches to repair unwanted false mappings that occur in Phase 2 text preprocessing. One is an ad hoc logic-based repair approach used before text preprocessing, employing an ontology-specific check to find common words that cause false mappings. The other repair approach is the post hoc large language model (LLM)-based approach, used after text preprocessing, which utilises the strong background knowledge provided by LLMs to repair non-existent and counter-intuitive false mappings. The experimental results indicate that these two approaches can significantly improve the matching correctness and the overall matching performance.

Sandaru Seneviratne, Sergio J. Rodríguez Méndez, Xuecheng Zhang et al.

Extraction of categorised named entities from text is a complex task given the availability of a variety of Named Entity Recognition (NER) models and the unstructured information encoded in different source document formats. Processing the documents to extract text, identifying suitable NER models for a task, and obtaining statistical information is important in data analysis to make informed decisions. This paper presents TNNT, a toolkit that automates the extraction of categorised named entities from unstructured information encoded in source documents, using diverse state-of-the-art Natural Language Processing (NLP) tools and NER models. TNNT integrates 21 different NER models as part of a Knowledge Graph Construction Pipeline (KGCP) that takes a document set as input and processes it based on the defined settings, applying the selected blocks of NER models to output the results. The toolkit generates all results with an integrated summary of the extracted entities, enabling enhanced data analysis to support the KGCP, and also, to aid further NLP tasks.

Tejal Shah, Fethi Rabhi, Pradeep Ray et al.

Research has shown that the general health and oral health of an individual are closely related. Accordingly, current practice of isolating the information base of medical and oral health domains can be dangerous and detrimental to the health of the individual. However, technical issues such as heterogeneous data collection and storage formats, limited sharing of patient information and lack of decision support over the shared information are the principal reasons for the current state of affairs. To address these issues, the following research investigates the development and application of a cross-domain ontology and rules to build an evidence-based and reusable knowledge base consisting of the inter-dependent conditions from the two domains. Through example implementation of the knowledge base in Protege, we demonstrate the effectiveness of our approach in reasoning over and providing decision support for cross-domain patient information.