Es 1: Ragionamento logico in un problema di persuasione.
Tutor: Irene Mazzotta

Probabilistic reasoning in predictive expert systems.
D. Spiegelhalter

Profiling your customers using bayesian networks
P.Sebastiani, M.Ramoni, A.Crea

Es 2: Apprendimento e validazione di una rete bayesiana.
Tutor: Fiorella de Rosis

Sensitivity analysis: an aid for belief-network quantification.
V.Coupe', L. van der Gaag and J.Habbema

Es 3: Analisi di sensibilità in una rete bayesiana
Tutor: Valeria Carofiglio

Bayesphone: precomputation of context-sensitive policies for inquiry and action in mobile devices
E.Horvitz et al

Es 4: Attivazione e aggiornamento di un modello di utente
Tutor: Valeria Carofiglio

Fall diagnosis using dynamic belief networks
A. Nicholson

Es 4bis: Modelli di utente nei dialoghi
Tutor: Valeria Carofiglio

Harnessing models of users' goals to mediate clarification dialogs in spoken language systems
H. Horvitz et al

Sto(ry)chastic: a bayesian network architecture for user modeling and computational storytelling
F. Sparacino

Building natural language generation systems
E.Reiter

Es 5: Elaborazione di piani del discorso.
Tutor: Irene Mazzotta

Building applied natural language generation systems
E.Reiter and R. Dale
An introduction to rhetorical structure theory
B.Mann

Da Marc Schroeder:
The "reference" publication for MARY is this one:
M. Schröder & J. Trouvain (2003). The German Text-to-Speech Synthesis System MARY: A Tool for Research, Development and Teaching. International Journal of Speech Technology.
It is available via http://mary.dfki.de/documentation/publications and via my publications page, http://www.dfki.de/~schroed/publications.html
The best way to understand how MARY interprets its input may be to look at how, e.g., APML is converted into RAWMARYXML.
The best for your students would be to ask questions on the mary-users mailing list (http://www.dfki.de/mailman/listinfo/mary-users)

Es 6: Generazione di messaggi speech-based
Tutor: Fiorella de Rosis e Irene Mazzotta

ILEX: an architecture for a dynamic hypertext system
M.O'Donnel, C.Mellish, J.Oberlander

Introduction to natural language understanding.
J.Allen

Es 7: Progettazione di un riconoscitore di frasi in linguaggio naturale con Phoenix.
Tutor: Fiorella de Rosis e Enzo Silvestri

ARTIMIS: Natural Dialogue Meets Rational Agency.
M.D.Sadek, P.Bretier and F.Panaget.

Es 8: Simulazione di un dialogo semplice basato su ATN
Tutor: Fiorella de Rosis

Generating socially appropriate tutorial dialogs
L.Johnson