Plan-Based Dialogue Management in a Physics Tutor
نویسنده
چکیده
This paper describes an application of APE (the Atlas Planning Engine), an integrated planning and execution system at the heart of the Atlas dialogue management system. APE controls a mixedinitiative dialogue between a human user and a host system, where turns in the ‘conversation’ may include graphical actions and/or written text. APE has full unification and can handle arbitrarily nested discourse constructs, making it more powerful than dialogue managers based on finitestate machines. We illustrate this work by describing Atlas-Andes, an intelligent tutoring system built using APE with the Andes physics tutor as the host.
منابع مشابه
Dialogue management for embedded training
We are developing an embedded training system to teach students to use complex software applications. Our tutor reasons strategically about its pedagogical plans. It uses a discourse model to communicate with the student and to guide its strategic decision making. We are developing the tutor using the Collagen platform for collaborative agent management, which provides a plan representation lan...
متن کاملDelivering Hints in a Dialogue-Based Intelligent Tutoring System
Hinting is an important tutoring tactic in one-on-one tutoring, used when the tutor needs to respond to an unexpected answer from the student. To issue a follow-up hint that is pedagogically helpful and conversationally smooth, the tutor needs to suit the hinting strategy to the student’s need while making the strategy fit the high level tutoring plan and the tutoring context. This paper descri...
متن کاملAn Approach to Increasing Programming Efficiency in Plan-Based Dialogue Systems
In this paper we use software engineering criteria to evaluate possible changes to a dialogue-based ITS. We have developed a prototype ITS, CAPE, that uses the APE reactive planning system as a platform for developing a small ITS based on CIRCSIM-Tutor, an existing medical tutor. CAPE primitives are untyped, like relations in a Prolog program, and can include elements of discourse, domain and p...
متن کاملClaus Zinn , Johanna D . Moore , and Mark G . Core Intelligent Information Presentation for Tutoring Systems
Effective human tutoring has been compared to a delicate balancing act. Students must be allowed to discover and correct problems on their own, but the tutor must intervene before the student becomes frustrated or confused. Natural language dialogue offers the tutor many ways to lead the student through a line of reasoning, and to indirectly notify the student of an error and use a series of hi...
متن کاملWhat Should the Tutor Do When the Student Cannot Answer a Question?
In this paper we describe how to simulate the behavior of a human tutor when the student cannot answer a question in a dialogue-based tutoring system. This paper describes an implementation of our analysis of human tutoring behavior using the simple plan-based framework of our tutoring system CIRCSIM-Tutor v. 2. By carefully choosing the retry strategies according to our categorization of the s...
متن کامل