Browsing by Author "Keet, C Maria"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Open Access
    The African wildlife ontology tutorial ontologies
    (2020-06-23) Keet, C Maria
    Background Most tutorial ontologies focus on illustrating one aspect of ontology development, notably language features and automated reasoners, but ignore ontology development factors, such as emergent modelling guidelines and ontological principles. Yet, novices replicate examples from the exercise they carry out. Not providing good examples holistically causes the propagation of sub-optimal ontology development, which may negatively affect the quality of a real domain ontology. Results We identified 22 requirements that a good tutorial ontology should satisfy regarding subject domain, logics and reasoning, and engineering aspects. We developed a set of ontologies about African Wildlife to serve as tutorial ontologies. A majority of the requirements have been met with the set of African Wildlife Ontology tutorial ontologies, which are introduced in this paper. The African Wildlife Ontology is mature and has been used yearly in an ontology engineering course or tutorial since 2010 and is included in a recent ontology engineering textbook with relevant examples and exercises. Conclusion The African Wildlife Ontology provides a wide range of options concerning examples and exercises for ontology engineering well beyond illustrating just language features and automated reasoning. It assists in demonstrating tasks concerning ontology quality, such as alignment to a foundational ontology and satisfying competency questions, versioning, and multilingual ontologies.
  • Thumbnail Image
    Item
    Open Access
    Grammars for generating isiXhosa and isiZulu weather bulletin verbs
    (2018) Mahlaza, Zola; Keet, C Maria
    The Met Office has investigated the use of natural language generation (NLG) technologies to streamline the production of weather forecasts. Their approach would be of great benefit in South Africa because there is no fast and large scale producer, automated or otherwise, of textual weather summaries for Nguni languages. This is because of, among other things, the complexity of Nguni languages. The structure of these languages is very different from Indo-European languages, and therefore we cannot reuse existing technologies that were developed for the latter group. Traditional NLG techniques such as templates are not compatible with 'Bantu' languages, and existing works that document scaled-down 'Bantu' language grammars are also not sufficient to generate weather text. In pursuance of generating weather text in isiXhosa and isiZulu - we restricted our text to only verbs in order to ensure a manageable scope. In particular, we have developed a corpus of weather sentences in order to determine verb features. We then created context free verbal grammar rules using an incremental approach. The quality of these rules was evaluated using two linguists. We then investigated the grammatical similarity of isiZulu verbs with their isiXhosa counterparts, and the extent to which a singular merged set of grammar rules can be used to produce correct verbs for both languages. The similarity analysis of the two languages was done through the developed rules' parse trees, and by applying binary similarity measures on the sets of verbs generated by the rules. The parse trees show that the differences between the verb's components are minor, and the similarity measures indicate that the verb sets are at most 59.5% similar (Driver-Kroeber metric). We also examined the importance of the phonological conditioning process by developing functions that calculate the ratio of verbs that will require conditioning out of the total strings that can be generated. We have found that the phonological conditioning process affects at least 45% of strings for isiXhosa, and at least 67% of strings for isiZulu depending on the type of verb root that is used. Overall, this work shows that the differences between isiXhosa and isiZulu verbs are minor, however, the exploitation of these similarities for the goal of creating a unified rule set for both languages cannot be achieved without significant maintainability compromises because there are dependencies that exist in one language and not the other between the verb's 'modules'. Furthermore, the phonological conditioning process should be implemented in order to improve generated text due to the high ratio of verbs it affects.
  • Thumbnail Image
    Item
    Open Access
    An Introduction to Ontology Engineering
    (University of Cape Town, 2018-07-16) Keet, C Maria
    An Introduction to Ontology Engineering is a free online textbook that provides an overview of ontology engineering, including logics and automated reasoning, methods and methodologies, top-down ontology development with foundational ontologies, and bottom-up strategies with non-ontological resources. It has three further specialized topics: Ontology-Based Data Access, multilingual ontologies and CNLs, and advanced modeling with language extensions. Each chapter contains review questions and exercises, and two sample assignments are included at the end. Answers are provided for a selection of the exercises. The approach to ontology engineering and the textbook’s contents are aimed at advanced undergraduate and postgraduate levels in computer science, and the book is structured accordingly. It could fit a semester-long course, covering roughly one chapter per week.
  • Thumbnail Image
    Item
    Open Access
    Modelling evolving clinical practice guidelines: a case of Malawi
    (2018) Msosa, Yamiko Joseph; Keet, C Maria; Densmore, Melissa
    Electronic medical record (EMR) systems are increasingly being adopted in low- and middle-income countries. This provides an opportunity to support task-shifted health workers with guideline-based clinical decision support to improve the quality of healthcare delivery. However, the formalization of clinical practice guidelines (CPGs) into computer-interpretable guidelines (CIGs) for clinical decision support in such a setting is a very challenging task due to the evolving nature of CPGs and limited healthcare budgets. This study proposed that a CIG modelling language that considers CPG change requirements in their representation models could enable semi-automated support of CPG change operations thereby reducing the burden of maintaining CIGs. Characteristics of CPG changes were investigated to elucidate CPG change requirements using CPG documents from Malawi where EMR systems are routinely used. Thereafter, a model-driven engineering approach was taken to design a CIG modelling framework that has a novel domain-specific modelling language called FCIG for the modelling of evolving CIGs. The CIG modelling framework was implemented using the Xtext framework. The national antiretroviral therapy EMR system for Malawi was extended into a prototype with FCIG support for experimentation. Further studies were conducted with CIG modellers. The evaluations were conducted to answer the following research questions: i) What are the CPG change requirements for modelling an evolving CIG? ii) Can a model-driven engineering approach adequately support the modelling of an evolving CIG? iii) What is the effect of modelling an evolving CIG using FCIG in comparison with the Health Level Seven (HL7) standard for modelling CIGs? Data was collected using questionnaires, logs and observations. The results indicated that finegrained components of a CPG are affected by CPG changes and that those components are not included explicitly in current executable CIG language models. The results also showed that by including explicit semantics for elements that are affected by CPG changes in a language model, smart-editing features for supporting CPG change operations can be enabled in a language-aware code editor. The results further showed that both experienced and CIG modellers perceived FCIG as highly usable. Furthermore, the results suggested that FCIG performs significantly better at CIG modelling tasks as compared to the HL7 standard, Arden Syntax. This study provides empirical evidence that a model-driven engineering approach to clinical guideline formalization supports the authoring and maintenance of evolving CIGs to provide up-to-date clinical decision support in low- and middle-income countries.