The Architecture of a Cooperative Respondent (Dissertation Proposal)

Abstract : If natural language question-answering (NLQA) systems are to be truly effective and useful, they must respond to queries cooperatively, recognizing and accommodating in their replies a questioner's goals, plans, and needs. Transcripts of natural dialogue demonstrate that cooperative responses typically combine several communicative acts: a question may be answered, a misconception identified, an alternative course of action described and justified. This project concerns the design of cooperative response generation systems, NLQA systems that are able to provide integrated cooperative responses. Two questions must be answered before a cooperative NLQA system can be built. First, what are the reasoning mechanisms that underlie cooperative response generation? In partial reply, I argue that plan evaluation is an important step in the process of selecting a cooperative response, and describe several tests that may usefully be applied to inferred plans. The second question is this: what is an appropriate architecture for cooperative NLQA (CNLQA) systems? I propose a four- level decomposition of the cooperative response generation process and then present a suitable CNLQA system architecture based on the blackboard model of problem solving. Keywords: Computer programming, Man computer interface; Cooperative response systems; Question answer systems; Architecture.

[1]  Sandra Carberry.  Modeling the User's Plans and Goals , 1988, Comput. Linguistics.

[2]  Timothy W. Finin,et al.  Acquiring a model of the user's beliefs from a cooperative advisory dialog , 1988 .

[3]  Sandra Carberry,et al.  Plan Recognition and Its Use in Understanding Dialog , 1989 .

[4]  Martha E. Pollack,et al.  Inferring domain plans in question-answering , 1986 .

[5]  Craig Cornelius,et al.  Computational Costs versus Benefits of Control Reasoning , 1987, AAAI.

[6]  Perry L. Miller,et al.  ATTENDING: Critiquing a Physician's Management Plan , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  M. Brady,et al.  Recognizing Intentions From Natural Language Utterances , 1983 .

[8]  Julia Hirschberg,et al.  A theory of scalar implicature , 1985 .

[9]  Earl David Sacerdoti,et al.  A Structure for Plans and Behavior , 1977 .

[10]  Victor R. Lesser,et al.  The Hearsay-II Speech-Understanding System: Integrating Knowledge to Resolve Uncertainty , 1980, CSUR.

[11]  Stephen Fickas,et al.  The Design and an Example Use of Hearsay-III , 1981, IJCAI.

[12]  Robert Wilensky,et al.  Intelligent agents as a basis for natural language interfaces , 1987 .

[13]  Barbara Hayes-Roth,et al.  A Blackboard Architecture for Control , 1985, Artif. Intell..

[14]  Bonnie Webber,et al.  Preventing False Inferences , 1984, Annual Meeting of the Association for Computational Linguistics.

[15]  H. Penny Nii,et al.  Blackboard Systems, Part Two: Blackboard Application Systems, Blackboard Systems from a Knowledge Engineering Perspective , 1986, AI Mag..

[16]  Robert Rubinoff,et al.  Adapting MUMBLE: Experience with Natural Language Generation , 1986, HLT.

[17]  John D. Gabbe,et al.  Transactional Blackboards , 1985, IJCAI.

[18]  Daniel D. Corkill,et al.  GBB: A Generic Blackboard Development System , 1986, AAAI.

[19]  Marc B. Vilain,et al.  The Restricted Language Architecture of a Hybrid Representation System , 1985, IJCAI.

[20]  Bonnie L. Webber,et al.  Living Up to Expectations: Computing Expert Responses , 1984, HLT.

[21]  James F. Allen,et al.  A Plan Recognition Model for Subdialogues in Conversations , 1987, Cogn. Sci..

[22]  R. Wilensky.  Planning and Understanding: A Computational Approach to Human Reasoning , 1983 .

[23]  Michael Brady,et al.  Cooperative Responses From a Portable Natural Language Database Query System , 1983 .

[24]  Daniel D. Corkill,et al.  Achieving Flexibility, Efficiency, and Generality in Blackboard Architectures , 1987, AAAI.

[25]  Timothy W. Finin,et al.  Natural language interactions with artificial experts , 1986, Proceedings of the IEEE.

[26]  Edmund H. Durfee,et al.  Incremental Planning to Control a Blackboard-based Problem Solver , 1986, AAAI.

[27]  Robert Balzer,et al.  HEARSAY-II: A Domain-Independent Framework for Expert Systems , 1980, AAAI.

[28]  Wolfgang Wahlster,et al.  Over-Answering Yes-No Questions: Extended Responses in a NL Interface to a Vision System , 1983, IJCAI.

[29]  Edward A. Feigenbaum,et al.  Signal-to-Symbol Transformation: HASP/SIAP Case Study , 1982, AI Mag..

[30]  Robert Wilensky.  Some Problems and Proposals for Knowledge Representation , 1987 .

[31]  Barbara Hayes-Roth,et al.  Integrating Diverse Reasoning Methods in the BB1 Blackboard Control Architecture , 1987, AAAI.

[32]  P L Miller,et al.  Medical plan-analysis by computer: critiquing the pharmacologic management of essential hypertension. , 1984, Computers and biomedical research, an international journal.

[33]  Eric Mays.  A Temporal Logic for Reasoning About Changing Data Bases in the Context of Natural Language Question-Answering , 1984, Expert Database Workshop.

[34]  James F. Allen.  Towards a General Theory of Action and Time , 1984, Artif. Intell..

[35]  Henry A. Kautz,et al.  Constraint Propagation Algorithms for Temporal Reasoning , 1986, AAAI.

[36]  Jack Minker,et al.  A Natural Language Database Interface That Provides Cooperative Answers , 1985, CAIA.

[37]  Francisco Corella.  Semantic Retrieval and Levels of Abstraction , 1984, Expert Database Workshop.

[38]  Eric Mays,et al.  Failures in Natural Language Systems: Applications to Data Base Query Systems , 1980, AAAI.

[39]  William A. Woods,et al.  Semantics and Quantification in Natural Language Question Answering , 1986, Adv. Comput..

[40]  Kathleen McKeown,et al.  Tailoring Explanations for the User , 1985, IJCAI.