This paper presents several ideas for dealing with parts of this broad problem. One is the use of presupposition to detect user assumptions. The second is relaxation of tests while parsing. The third is a general technique for responding intelligently when no parse can be found. All of these ideas have been implemented and tested in one of two natural language systems. Some of the ideas are heuristics that might be employed by humans; others are engineering solutions for the problem of practical natural language systems

This paper discusses aspects of a computational model for the semantics of why-questions which are relevant to the implementation of an explanation component in a natural language dialogue system. After a brief survey of all of the explanation components which have been implemented to date, some of the distinguishing features of the explanation component designed and implemented by the author are listed. In the first part of the paper the major types of signals which, like the word why, can be used to set the explanation component into action are listed, and some ways of recognizing them automatically are considered. In addition to these linguistic signals, communicative and cognitive conditions which can have the same effect are discussed. In the second part the various schemata for argumentative dialogue sequences which can be handled by the explanation component in question are examined. Particular attention is paid to problems arising in connection with the iteration of why-questions and the verbalization of multiple justifications. Finally schemata for metacommunicative why-questions and for why-questions asked by the user are investigated

Many modern human-computer interfaces are difficult for people to use. This is often because these interfaces make no significant attempt to communicate with the people who use them. In other words, these interfaces are uncooperative: They do not adapt themselves to their users' needs and they are insensitive to human foibles. Ordinary command line interfaces such as that of the UNIX C shell (csh) are intolerant of even the most simple input errors, even when those errors have obvious corrections. An "intelligent" UNIX shell interface, on the other hand, would make use of knowledge and interaction context in order to interpret --- and as necessary, correct --- its users' commands. Valet is a prototype of such an "intelligent" interface to the UNIX C shell. Valet adds knowledge-based parsing and input correction to the shell by encapsulating an ordinary C shell process within a framework that allows Valet to control the shell's input and output. Valet intercepts shell commands and par...

kely that, in addition to the content (the argument of the discourse) indications will appear on the gramatical choices made by the author of the text (or the speaker) when expressinl himself on that argument (how the argument is expressed). When these indications have been adequately quantified, they can be used to correctly select the perceptive sirsicKles (as defined in [Kaplan 72]) to be adopted in order to achieve reater efficiency in the analysis of the foliowin[ part of the text. 4. For our experiments we have used ATNSYfi [Stock 76], and an Italian Srammar with n - 50 (127 arcs) [Csppelli et al.77]. In this system, search is depth-first and the parser interacts with a heuristic machanism which orders the arcs according to s probability evaluation. This probability evaluation is dependent on the path vhich led to the current node and ts also a function of the statistical data accumulated during previous analyses of a "coherent" text. The mechanism can be tvided into tvo stage

Introduction Jerry R. Hobbs SRI International Progress on natural language interfaces can perhaps be stimulated or directed by imagining the ideal natural language system of the future. What features (or even design philosophies) should such a system have in order to becomo an integral part of our work environments? What scaled-down versions of these features might be possible in the near future in "simple service systems" 2]? These issues can be broken down into the following four questions: 1. What are the significant features of the environment in which the system will reside? The system will be one participant in an intricate inforuation network, depending on a continually reinforced shared complex of knowl- edge [9]. To be an integral part of this environment, the system must possess some of the shared knowledge and perhaps must participate in its reinforcement, e.g. via explanations, [9], [2]. 2. Investigations of person-person communication should tell us what person-sys

In this paper we describe a syntactic semantic parser of spo-. ken sentences pertaining to a subset of natural Italian language. Error-free and fast analysis, partial interpretation ability, man-machine dialogue trend, different semantic environment adaptability and natural language usage are its main characteristics. All of these features are supported by a technique of input reliability evaluation. Particular attention is devoted to the description of the knowledge internal representation and of the mechanism that manages, at different points of the analysis, the whole process. I. PARSER QUALIFICATIONS The parser to be described performs its analysis starting from an intrinsically unreliable input that is the result of an isolated word speech recognizer. The lack of certainty on the single items of the input sentence is one of the main problems in such a vocal parser. The representation of each uttered word, following the recognition stage, is, in fact, an ordered list of possible interpretations with associated dissimilarity measures. As a consequence, it is possible to have doubts not only about every single word of the sentence, but also on complete sentence parts. Moreover, irrecoverable recognition errors may require the capability of parsing incomplete sentences.

Abstract not found