Showing papers on "Question answering published in 1974"

Language and Knowledge of the World.

Abstract: of knowledge. According to one view, information is stored mentally, much as in a richly illustrated encyclopedia or an audiovisual film library, with knowledge of the world represented as perceptual images of concrete things and events accompanied by relevant verbal descriptions and commentaries. According to the other view, the perceptual and verbal forms are only superficial expressions of an abstract informational base more

Computer generation of natural-language from a deep conceptual base.

Abstract: : For many tasks involving communication between humans and computers it is necessary for the machine to produce as well as understand natural language. The authors describes an implemented system which generates English sentences from Conceptual Dependency networks, which are unambiguous, language- free representations of meaning. The system is designed to be task independent and thus capable of providing the language generation mechanism for such diverse problem areas as question answering, machine translation, and interviewing.

Learning from Prose Text: Effects of Readability Level, Inserted Question Difficulty, and Individual Differences.

Abstract: Studied immediate and 2-wk retention as a function of 3 levels of text readability and 2 levels of inserted postquestion difficulty. 28 undergraduates served as Ss. The inserted postquestion treatment was modified to permit review of text after question answering. A traditional control group was req

SOPHIE: a pragmatic use of artificial intelligence in CAI

Abstract: This paper describes a fully operational AI-CAI system (accessible over the ARPANET) which incorporates Artificial Intelligence techniques to perform question answering, hypothesis verification and theory formation activities in the domain of electronic troubleshooting. Much of its logical or inferencing capabilities are derived from uses of simulation models in conjunction with numerous procedural specialists. The system also includes a highly tuned structural parser for allowing the student to communicate in natural language. Although the system is extremely large it is sufficiently fast to be thoroughly exercised in a training or classroom environment.

The Effectiveness of Natural Language in Science Indexing and Retrieval.

Abstract: This paper examines the implications of the findings of evaluative tests regarding the retrieval performance of natural language in various subject fields. It suggests parallel investigations into the structure of natural language, with particular reference to terminology, as used in the different branches of basic science. The criteria for defining the terminological consistency of a subject are formulated and a measure suggested for determining the degree of terminological consistency.

MRPPS—An interactive refutation proof procedure system for question-answering

Abstract: In this paper a system termed the Maryland refutation proof procedure system (MRPPS) is described. MRPPS is an interactive system which gives the user the ability to create and maintain a core-bound data base and to input queries either as well-formed formulas in the first-order predicate calculus or as clauses. MRPPS consists of three basic components: (1) a set of inference rules for making logical deductions, many of which are based on the resolution principle; (2) a search strategy for heuristically determining the sequence in which to select base clauses and to perform deductions on clauses already generated; and (3) a base clause selection strategy that uses heuristic and semantic information for determining which data axioms and general axioms are to be brought to bear on the problem. These three components are described and MRPPS is compared to related work.

Representing negation in a planner system

Abstract: A program is described which carries on a dialogue with the operator, accepting English statements and questions, noting the statements and answering the questions. A method is described for representing negative information. The program goes beyond previous question-answering systems in that new information can be given in English even where this entails selectively removing older information. Universal and existential 'quantifiers* and negation may be used in both statements and questions. The treatment of the quantifiers is outlined. The program uses POPLER 1.5, a PLANNER-like system.

Natural language information storage and retrieval system for nuclear medicine: two years' experience.

Abstract: For two years an information storage and retrieval system originally designed for pathology diagnoses has also been used for nuclear medicine reports. An input translator accepts the free text which is automatically indexed. A thesaurus automatically expands a search request to include related terms. Logical searches cross-referencing these two patient data files result in increased specificity of retrieved material. Expansion of the data base by laboratory and medical record summaries in natural language will further improve cross-referencing and increase specificity of searches.

Natural Language Based Information Retrieval

Abstract: : A program which accepts natural language queries can allow a nontechnical user to easily obtain information from a large non-uniform data base. To date most natural language systems have used parsers whose operation bears dubious resemblance to human language understanding and furthermore, these systems have proved to be difficult to extend to new data bases. This paper discusses the design of a new natural language data base interrogation system which should overcome these difficulties.

Global parallel unification for large question-answering systems

Abstract: An efficient means of storing data in a first-order predicate calculus theorem-proving system is described. The data structure is oriented for large scale question-answering (QA) systems. An algorithm is outlined which uses the data structure to unify a given literal in parallel against all literals in all clauses in the data base. The data structure permits a compact representation of data within a QA system. Some suggestions are made for heuristics which can be used to speed-up the unification algorithm in systems.

Some ideas on semantic memory in automatic learning of heuristics

Abstract: This paper is concerned with the problem of computer semantic memory, i. e. with the problem of representing general knowledge about, a given world. The sematic memory issue is raised in the context of machiue learning of heuristics and the connection with the problem of machine representation of knowledge is emphasized. The guidelines for the implementation of a sematic memory are presented and attention is given to the design of the processes for storing and retrieving information. The problem of knowledge representation is tackled in its, general form, so that the proposed semantic memory may be of interest also in other fields, like Natural Lauguage Understanding, Question Answering, Theorem Proving.