Modelling conceptual change: An interdisciplinary approach -- Refining numerical terms in horn clauses -- Handling continuous data in top-down induction of first-order rules -- Inductive inference of tree automata by recursive neural networks -- A computational model of misunderstandings in Agent Communication -- Wide-Coverage lexicalized grammars -- Flexible response choice using problem-solving plans and rhetorical relations -- A variant of Earley parsing -- Autonomous robot navigation using a reactive agent -- A hybrid architecture for autonomous agents -- 3-D Facets construction for stereovision -- Extraction of discriminant features from image fractal encoding -- Learning relational concepts at different levels of granularity -- Inferring minimal rule covers from relations -- Corpus-driven unsupervised learning of verb subcategorization frames -- Learning the syntax and semantic rules of an ECG grammar -- Introducing abduction into (Extensional) inductive logic programming systems -- An efficient algorithm for temporal abduction -- Experimental analysis of the computational cost of evaluating Quantified Boolean Formulae -- A proof theory for tractable approximations of propositional reasoning -- Embedding minimal knowledge into autoepistemic logic -- User model-based information filtering -- A comparative analysis of Horn models and Bayesian Networks for diagnosis -- Multi-agent negotiation and planning through knowledge contextualization -- From task delegation to role delegation -- Automated reasoning on-board autonomous spacecraft -- A weakly backjumping strategy to solve hard scheduling problems -- Compiling task networks into partial order planning domains -- A hybrid approach to hypertext generation -- Generating user-adapted hypermedia from discourse plans -- WordNet for Italian and its use for lexical discrimination -- Efficient support for reactive rules in prolog -- Reasoning with behavioural knowledge in application domain models -- How to solve qualification and ramification using Dijkstra's semantics for programming languages -- Towards a qualitative Representation of Linguistic Negation of Nuanced Properties -- CBET: A Case Base Exploration Tool -- Learning feature weights for CBR: Global versus local -- CompAss: A system for plans of study compilation -- A prototypal system for data-validation -- ODB-Tools: A description logics based tool for schema validation and semantic query optimization in object oriented databases -- Processing paper documents with WISDOM -- REGAL3.2: FOL concept learning by cooperative genetic algorithms -- IDL: A prototypical intelligent digital library service -- An object-oriented architecture for the DRS scheduling problem -- MASMA: A personal assistant for meetings management.

This book constitutes the refereed proceedings of the 5th Congress of the Italian Association for Artificial Intelligence, AI*IA 97, held in Rome, Italy, in September 1997. The 37 revised full papers and 8 system descriptions presented in the volume were selected from 88 papers submitted. The papers are organized in topical sections on machine learning; natural language processing; perception, vision and robotics; distributed artificial intelligence; and planning.