This book constitutes the refereed proceedings of the XXIInd International Conference on AIxIA 2023 - Advances in Artificial Intelligence, AIxIA 2023, held in Rome, Italy, during November 6-10, 2023.
The 33 full papers included in this book were carefully reviewed and selected from 53 submissions. They were organized in topical sections as follows: Argumentation and Logic Programming, Natural Language Processing, Machine Learning, Hybrid AI and Applications of AI.
Inhaltsverzeichnis
Argumentation and Logic Programming
. - ABALearn: An automated logic-based learning system for ABA frameworks. - Deriving Dependency Graphs from Abstract Argumentation Frameworks. - ReConf: An Automatic Context-based Software Reconfiguration Tool for Autonomous Vehicles using Answer-Set Programming. - Mining contrast sequential patterns with ASP. -
Ontologies
. - An ontological modelling of reason-based preferences. - A Defeasible Description Logic for Abduction. - Ontology-based Data Management in Healthcare: The Case of the Italian Arthroplasty Registry. -
Planning
. - A Structure-Sensitive Translation from Hybrid to Numeric Planning. - Intrinsically Motivated High-Level Planning for Agent Exploration. -
Natural Language Processing
. - Mining Argument Components in Essays at Different Levels. - Unraveling ChatGPT: A Critical Analysis of AI-Generated Goal-Oriented Dialogues and Annotations. - Scaling Large Language Models to the Extreme: Neural Semantic Processing of Multiple Tasks in Italian. - Named Entity Recognition and Linking for Entity Extraction from Italian Civil Judgements. -
Machine Learning
. - CENTAURO: an Explainable AI Approach for Customer Loyalty Prediction in Retail Sector. - Toward Novel Optimizers: A Moreau-Yosida View of Gradient-based Learning. - Mastering the Card Game of Jaipur through Zero-knowledge Self-Play Reinforcement Learning and Action Masks. - Uncovering Bias in the Face Processing Pipeline: An Analysis of Popular and State-of-the-Art Algorithms Across Demographic Groups. - A multi-label classification study for the prediction of long-covid syndrome. - PAUL-2: An Upgraded Transformer-Based Redesign of the Algorithmic Composer PAUL. -
Robotics and Perception
. - Understanding the Effect of Deep Ensembles in LiDAR-based Place Recognition. - Enanching LiDAR performance: Robust De-skewing Exclusively Relying o n Range Measurements. - Can Existing 3D Monocular Object Detection Methods Work in Roadside Contexts? A Reproducibility Study. - Embedding Shepard' s Interpolation into CNN Models for Unguided Depth Completion. - Performance evaluation of depth completion neural networks for various RGB-D camera technologies in indoor scenario. -
Hybrid AI
. - Inference in Probabilistic Answer Set Programming under the Credal Semantics. - Efficient Modal Decision Trees. - Clique-TF-IDF: A New Partitioning Framework based on Dense Substructures. - Combining Contrastive Learning and Knowledge Graph Embeddings to develop medical word embeddings for the Italian language. -
Applications of AI
. - Recognizing the Style, Genre, and Emotion of a Work of Art Through Visual and Knowledge Graph Embeddings. - Combining genetic algorithms and temporal constraint satisfactionfor recommending personalized tourist itineraries. - Towards Automatic Digitalization of Railway Engineering Schematics. - Election Manipulation in Social Networks with Single-Peaked Agents. - Learning to Prompt in the Classroom to Understand AI Limits: A pilot study.