Giacomo Ferrari

Natural language input for scene generation

In this paper a system which understands and conceptualizes scenes descriptions in natural language is presented. Specifically, the following components of the system are described: the syntactic analyzer, based on a Procedural Systemic Grammar, the semantic analyzer relying on the Conceptual Dependency Theory, and the dictionary.

Framework for a model of dialogue

In this paper we present a general model of cmmnunication applied to the special case of dialogue. Our broad perspective aims to account for the many facets of human dialogue within a singl~ theoretical framework. In particular, our projects aim of incorporating relevant non-verbal communicative acts from the person-machine interface make it essential that the description of communication be sufficiently broad.

A two-level dialogue representation

In this paper a two level dialogue representation system is presented. It is intended to recognize the structure of a large range of dialogues including some nonverbal communicative acts which may be involved in an interaction. It provides a syntactic description of a dialogue which can be expressed in terms of re-writing rules. The semantic level of the proposed representation system is given by the goal and subgoal structure underlying the dialogue syntactic units. Two types of goal are identified; goals which relate to the content of the dialogue, and those which relate to communicating the content.

Man-Machine interaction in natural language: Computational models of dialogue

This article presents a state-of-the-art review of studies on computational modeling of dialogue. Particular attention is given to the treatment of ill-formed input, the prevention of the hearer’s misconceptions, the inference of the speaker’s plans, the generation of language, and the recognition of dialogue focus—particularly in terms of implications for linguistics. Specifications and initial results of some recent studies carried out by the author are provided.

Extended access to the left context in an ATN parser

Some Italian sentences related to linguistic phenomena largely known and recently discussed by many computational linguists are discussed in the framework of ATN. They offer certain difficulties which seem to suggest a substantial revision of the ATN formalism. The theoretical assumptions and an experimental implementation of such a revision are presented, together with examples. Many related theoretical points such as some psycholinguistic implications and the relationship between deterministic and non-Jeterministic hypothesis are also briefly discussed.

Explanation Strategies in a Tutoring System

In this paper the design and implementation of an Intelligent Tutoring System will be described (ESPRIT BRA IDEAL, Interactive Dialogues for Explanation And Learning3). A special attention will be given on the explanation strategy selection mechanism, which allows the system to provide explanation about a particular domain to a user, in a most cooperative way. The advantages provided by the particular context in which the interaction takes place (namely, one of tutoring), allows the developer to use techniques and devices which showed to be particularly efficient respect to other manmachine interaction systems.

Dialogue Modeling and Response Generation in CFID@, a robust man-machine interface system

This paper will describe a demonstration dialogue system, developed within the ESPRIT Project #527 CFID. The general aim of the project has been to carry research in the field of human communication, in order to reach a deeper insight on the general mechanisms which allow people to communicate, despite communication failures, misunderstandings, and many other disturbances. Communication has been studied as a complex mixture of verbal and non-verbal communication, and explicit and inferred message understanding. The dialogue model and the response generation techniques are described in more detail.

Generalized memory manipulating actions for parsing natural language

Current (computational) linguistic theories have developed specific formalisms for representing linguistic phenomena such as unbounded dependencies, relatives, etc. In this contribution we present a model of linguistic structures storing and accessing, which accounts for the same phenomena in a procedural way. Such a model has been implemented in the frame of an ATN parser.