Alberto Bugarín

This special issue follows the discussions held at the 2024 Edition of The Workshop on the History of Artificial Intelligence (WHAI 2024), celebrated in Santiago de Compostela within the framework of the 27th European Conference on Artificial Intelligence (ECAI 2024). In WHAI, presentations were held about the starting and evolution of artificial intelligence (AI) in several European regions, and about the contribution of European research and researchers to specific paradigms and to the history of AI in general. Following these discussions, this issue includes the extended versions of two papers presented at WHAI, one on how AI originated at the University of Edinburgh and another on the contributions of European researchers to the foundations and applications of model-based reasoning. The special issue is now enriched with a historical perspective of AI in Catalonia, the motivation for the AI community to build and disseminate the timeline of the History of AI in Europe and a proposal for a Collective Memory of Artificial Intelligence, which expands the timeline initiative. All papers are a contribution to The History of AI Timeline, an open project for the future, which also began with WHAI2024 and will be updated and enriched through the discussions of subsequent editions of WHAI.

Nonalcoholic steatohepatitis (NASH) is a common disease that ultimately can lead to the development of end-stage liver disease, cirrhosis, or hepatocellular carcinoma. An early prediction of NASH provides an opportunity to make an appropriate strategy for prevention, early diagnosis, and treatment. The most accurate approach for NASH diagnostics is a liver biopsy, which can lead to various complications for the patient. Many papers have studied non-invasive machine learning (ML)-driven approaches to early non-invasive NASH prediction; however, to the best of our knowledge, none of the works considered the problem of explainability of the trained ML models to the medical experts. In this work, we address this issue. We use the National Institute of Diabetes and Digestive and Kidney Diseases (NIDDK) nonalcoholic fatty liver disease adult database to train different ML models and propose the technique to explain their predictions. We compare the explanations obtained from a transparent model (Decision Tree) and a non-transparent model (Random Forest). Furthermore, we analyze the quality of explanation prediction by objective means and with a user study involving 11 medical practitioners. Our findings show that there is no significant difference in the perception of explanation obtained from transparent and non-transparent models, and that the explanation of the models’ predictions slightly increases their usability and trustworthiness for real practitioners, enhancing their practical adoption in clinical settings.

Bayesian Networks (BNs) are probabilistic graphical models used to represent variables and their conditional dependencies, making them highly valuable in a wide range of fields, such as radiology, agriculture, neuroscience, construction management, medicine, and engineering systems, among many others. Despite their widespread application, the reusability of BNs presented in papers that describe their application to real-world tasks has not been thoroughly examined. In this paper, we perform a structured survey on the reusability of BNs using the PRISMA methodology, analyzing 147 papers from various domains. Our results indicate that only 18% of the papers provide sufficient information to enable the reusability of the described BNs. This creates significant challenges for other researchers attempting to reuse these models, especially since many BNs are developed using expert knowledge elicitation. Additionally, direct requests to authors for reusable BNs yielded positive results in only 12% of cases. These findings underscore the importance of improving reusability and reproducibility practices within the BN research community, a need that is equally relevant across the broader field of Artificial Intelligence.

Nikolay Babakov, Ehud Reiter, Alberto Bugarín-Diz. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 4: Student Research Workshop). 2025.

In this work, we propose a novel method for Bayesian Networks (BNs) structure elicitation that is based on the initialization of several LLMs with different experiences, independently querying them to create a structure of the BN, and further obtaining the final structure by majority voting. We compare the method with one alternative method on various widely and not widely known BNs of different sizes and study the scalability of both methods on them. We also propose an approach to check the contamination of BNs in LLM, which shows that some widely known BNs are inapplicable for testing the LLM usage for BNs structure elicitation. We also show that some BNs may be inapplicable for such experiments because their node names are indistinguishable. The experiments on the other BNs show that our method performs better than the existing method with one of the three studied LLMs; however, the performance of both methods significantly decreases with the increase in BN size.

The article emphasizes the critical importance of language generation today, particularly focusing on three key aspects: Multitasking, Multilinguality, and Multimodality, which are pivotal for the Natural Language Generation community. It delves into the activities conducted within the Multi3Generation COST Action (CA18231) and discusses current trends and future perspectives in language generation.

Prediction of the remaining times of a business process execution is one of the main challenges of process mining, being critical for many organisations. In this work we present a new approach based on the structural analysis of partial traces, each one is associated with a state of the transition system that describes the log behaviour. From this analysis, a set of parameters or attributes that characterise each partial execution of the process is obtained. The hypothesis behind it is that the remaining time to finish the process execution depends on these structural features. Once this set of attributes is obtained for each transition system state, using of the linear regression technique is utilized to predict the remaining time of the business process for each state. Experiments with eight well-known real-life datasets show that our approach outperforms the baseline model in the three metrics considered. We also analysed the performance of our approach when combined with two attribute selection methods, in order to demonstrate the estimation accuracy in regard to the time consumed in the calculation of the remaining time estimation. Experimental results indicate that the Forward Best-First method provides a good balance between estimation accuracy and computation time consumed.