User ' s Inferences
نویسنده
چکیده
In this paper, we describe a content planning mechanism which takes into consideration a user's possible inferences in order to generate the most concise discourse that achieves a given communicative goal. The consideration of a user's inferences results in the addition of information that addresses erroneous inferences , and the omission of easily inferred information. Given a communicative goal, our mechanism applies inference rules in backward reasoning mode to plan rhetorical devices that achieve this goal, and subsequently in forward reasoning mode to conjecture the eeect of these rhetorical devices on the user's beliefs. This process results in one or more sets of rhetorical devices which achieve the intended communicative goal. Each set is then minimized, and the most concise among these sets is selected. These ideas have been implemented in a system called WISHFUL, which generates explanations about concepts.
منابع مشابه
Technical Correspondance - A Note On The Utility Of Computing Inferences In A Real Data Base Query Environment
It is quite clear that as computer systems are made available to a wider class of more naive users than at present, the interfaces to these systems will need to have properties which have been termed "cooperative", "user friendly" and the like. One of the many desirable features of such an interface is the ability to take into account not only a user's direct input, but also things which are im...
متن کاملAvoiding Misconstruals in Database Systems: A Default Logic Approach
This paper describes a cooperative interface that, using suitable user models, alters the processing of the user’s queries to include additional information that will block faulty inferences. In a sense, the interface actively teaches the user facts about the database that he did not explicitly asked for. User interaction with the database then becomes a learning and diseovery process guided by...
متن کاملMultistrategy Task-adaptive Learning Using Dynamically Interlaced Hierarchies: A Methodology and Initial Implementation of INTERLACE
This research concerns the development of a methodology for representing, planning and executing multitype inferences in a multistrategy task-adaptive learning system. These inferences, defined in the Inferential Theory of Learning as knowledge transmutations, are generic types of knowledge operators, and are assumed to underlie all learning processes. The paper shows how several basic knowledg...
متن کاملKnowledge Engineering for Affective Bi-Modal Human-Computer Interaction
This paper presents knowledge engineering for a system that incorporates user stereotypes as well as a multi criteria decision making theory for affective interaction. The system bases its inferences about students’ emotions on user input evidence from the keyboard and the microphone. Evidence form these two modes is combined by a user modelling component underlying the user interface. The user...
متن کاملWeb pages ranking algorithm based on reinforcement learning and user feedback
The main challenge of a search engine is ranking web documents to provide the best response to a user`s query. Despite the huge number of the extracted results for user`s query, only a small number of the first results are examined by users; therefore, the insertion of the related results in the first ranks is of great importance. In this paper, a ranking algorithm based on the reinforcement le...
متن کامل