Search

This paper discusses the different roles that explicit knowledge, in particular ontologies, can play in Explainable AI and in the development of human-centric explainable systems and intelligible explanations. We consider three main perspectives in which ontologies can contribute significantly, namely reference modelling, common-sense reasoning, and knowledge refinement and complexity management. We overview some of the existing approaches in the literature, and we position them according to these three proposed perspectives. The paper concludes by discussing what challenges still need to be addressed to enable ontology-based approaches to explanation and to evaluate their human-understandability and effectiveness., Comment: Submitted to the Neurosymbolic AI journal: https://www.neurosymbolic-ai-journal.com/system/files/nai-paper-683.pdf

As systems based on opaque Artificial Intelligence (AI) continue to flourish in diverse real-world applications, understanding these black box models has become paramount. In response, Explainable AI (XAI) has emerged as a field of research with practical and ethical benefits across various domains. This paper not only highlights the advancements in XAI and its application in real-world scenarios but also addresses the ongoing challenges within XAI, emphasizing the need for broader perspectives and collaborative efforts. We bring together experts from diverse fields to identify open problems, striving to synchronize research agendas and accelerate XAI in practical applications. By fostering collaborative discussion and interdisciplinary cooperation, we aim to propel XAI forward, contributing to its continued success. Our goal is to put forward a comprehensive proposal for advancing XAI. To achieve this goal, we present a manifesto of 27 open problems categorized into nine categories. These challenges encapsulate the complexities and nuances of XAI and offer a road map for future research. For each problem, we provide promising research directions in the hope of harnessing the collective intelligence of interested stakeholders.

Rice is the second most important cereal crop worldwide, and the first in terms of number of people who depend on it as a major staple food. Rice blast disease is the most important biotic constraint of rice cultivation causing each year millions of dollars of losses. Despite the efforts for breeding new resistant varieties, agricultural practices and chemical control are still the most important methods for disease management. Thus, rice blast forecasting is a primary tool to support rice growers in controlling the disease. In this study, we compared four models for predicting rice blast disease, two operational process-based models (Yoshino and WARM) and two approaches based on machine learning algorithms (M5Rules and RNN), the former inducing a rule-based model and the latter building a neural network. In situ telemetry is important to obtain quality in-field data for predictive models and this was a key aspect of the RICE-GUARD project on which this study is based. According to the authors, this is the first time process-based and machine learning modelling approaches for supporting plant disease management are compared.

Explainability in Artificial Intelligence has been revived as a topic of active research by the need of conveying safety and trust to users in the `how' and `why' of automated decision-making. Whilst a plethora of approaches have been developed for post-hoc explainability, only a few focus on how to use domain knowledge, and how this influences the understandability of global explanations from the users' perspective. In this paper, we show how ontologies help the understandability of global post-hoc explanations, presented in the form of symbolic models. In particular, we build on Trepan, an algorithm that explains artificial neural networks by means of decision trees, and we extend it to include ontologies modeling domain knowledge in the process of generating explanations. We present the results of a user study that measures the understandability of decision trees using a syntactic complexity measure, and through time and accuracy of responses as well as reported user confidence and understandability. The user study considers domains where explanations are critical, namely, in finance and medicine. The results show that decision trees generated with our algorithm, taking into account domain knowledge, are more understandable than those generated by standard Trepan without the use of ontologies.

Ontology engineering is a hard and error-prone task, in which small changes may lead to errors, or even produce an inconsistent ontology. As ontologies grow in size, the need for automated methods for repairing inconsistencies while preserving as much of the original knowledge as possible increases. Most previous approaches to this task are based on removing a few axioms from the ontology to regain consistency. We propose a new method based on weakening these axioms to make them less restrictive, employing the use of refinement operators. We introduce the theoretical framework for weakening DL ontologies, propose algorithms to repair ontologies based on the framework, and provide an analysis of the computational complexity. Through an empirical analysis made over real-life ontologies, we show that our approach preserves significantly more of the original knowledge of the ontology than removing axioms., Comment: To appear AAAI 2018

Conceptual blending is a powerful tool for computational creativity where, for example, the properties of two harmonic spaces may be combined in a consistent manner to produce a novel harmonic space. However, deciding about the importance of property features in the input spaces and evaluating the results of conceptual blending is a nontrivial task. In the specific case of musical harmony, defining the salient features of chord transitions and evaluating invented harmonic spaces requires deep musicological background knowledge. In this paper, we propose a creative tool that helps musicologists to evaluate and to enhance harmonic innovation. This tool allows a music expert to specify arguments over given transition properties. These arguments are then considered by the system when defining combinations of features in an idiom-blending process. A music expert can assess whether the new harmonic idiom makes musicological sense and re-adjust the arguments (selection of features) to explore alternative blends that can potentially produce better harmonic spaces. We conclude with a discussion of future work that would further automate the harmonisation process., Comment: 8 pp; submitted to 7th International Conference on Computational Creativity

For most biophysical domains, differences in model structures are seldom quantified. Here, we used a taxonomy-based approach to characterise thirteen rice models. Classification keys and binary attributes for each key were identified, and models were categorised into five clusters using a binary similarity measure and the unweighted pair-group method with arithmetic mean. Principal component analysis was performed on model outputs at four sites. Results indicated that (i) differences in structure often resulted in similar predictions and (ii) similar structures can lead to large differences in model outputs. User subjectivity during calibration may have hidden expected relationships between model structure and behaviour. This explanation, if confirmed, highlights the need for shared protocols to reduce the degrees of freedom during calibration, and to limit, in turn, the risk that user subjectivity influences model performance.

Predicting rice (Oryza sativa) productivity under future climates is important for global food security. Ecophysiological crop models in combination with climate model outputs are commonly used in yield prediction, but uncertainties associated with crop models remain largely unquantified. We evaluated 13 rice models against multi-year experimental yield data at four sites with diverse climatic conditions in Asia and examined whether different modeling approaches on major physiological processes attribute to the uncertainties of prediction to field measured yields and to the uncertainties of sensitivity to changes in temperature and CO2 concentration [CO2]. We also examined whether a use of an ensemble of crop models can reduce the uncertainties. Individual models did not consistently reproduce both experimental and regional yields well, and uncertainty was larger at the warmest and coolest sites. The variation in yield projections was larger among crop models than variation resulting from 16 global climate model-based scenarios. However, the mean of predictions of all crop models reproduced experimental data, with an uncertainty of less than 10 percent of measured yields. Using an ensemble of eight models calibrated only for phenology or five models calibrated in detail resulted in the uncertainty equivalent to that of the measured yield in well-controlled agronomic field experiments. Sensitivity analysis indicates the necessity to improve the accuracy in predicting both biomass and harvest index in response to increasing [CO2] and temperature.