Showing papers on "Question answering published in 1984"

Designing a Portable Natural Language Database Query System

Abstract: One barrier to the acceptance of natural language database query systems is the substantial installation effort required for each new database. Much of this effort involves the encoding of semantic knowledge for the domain of discourse, necessary to correctly interpret and respond to natural language questions. For such systems to be practical, techniques must be developed to increase their portability to new domains.This paper discusses several issues involving the portability of natural language interfaces to database systems, and presents the approach taken in CO-OP — a natural language database query system that provides cooperative responses to English questions and operates with a typical CODA-SYL database system. CO-OP derives its domain-specific knowledge from a lexicon (the list of words known to the system) and the information already present in the structure and content of the underlying database. Experience with the implementation suggests that strategies that are not directly derivative of cognitive or linguistic models may nonetheless play an important role in the development of practical natural language systems.

The Logic of Incomplete Knowledge Bases

Abstract: Some formal representation issues underlying the use of incomplete knowledge bases are discussed. An incomplete knowledge base is one that has only partial knowledge of the application domain. It is argued that a language that can refer to both the application domain and to the state of the knowledge base is required to specify and to question an incomplete knowledge base. A formal logical language with this expressive ability is presented and its semantics and proof theory are defined. It is also shown how different the use of the language must be, depending on whether the interaction involves querying or defining the knowledge base.

Conversing with management information systems in a natural language

Abstract: A key objective of information systems is to provide effective communication between their users and the information they contain. This was the idea behind the development of a decision calculus for increasing communication between models and managers [30], and behind management decision systems that use interactive graphics to enhance the interface between models and managers [38]. It is also part of the rationale for such interactive decision-making environments as operations rooms [6], decision rooms [21], and planning laboratories [45], which assist groups of senior executives with problem identification and decision making; and or for decision support systems (DSS), which help managers to solve unstructured or semistructured problems by providing convenient access to various information sources, including information retrieved from files or provided by decision models [3, 15, 26, 27]. The interrelationship among data, models, and the user interface is spelled out in the work of Sprague [39] and Sprague and Carlson [40]. They identify three major functions of a DSS: data management, model management, and dialogue management. The dialogue between a DSS and its users may take many forms-menus or structured query languages, for instance. We are concerned here with a flexible interface: natural language query processors that allow a user to instruct or query a DSS using a large subset of the user's natural language.

Communicating with databases in natural language

Abstract: In the first chapters is a full description of natural languages and interface to relational database. Natural language processing and the use of PROLOG are discussed. Features include also a practical discussion of parsing natural language with accompanying programs in PROLOG

Testing of a natural language retrieval system for a full text knowledge base

Abstract: “A Navigator of Natural Language Organized Data” (ANNOD) is a retrieval system which combines use of probabilistic, linguistic, and empirical means to rank individual paragraphs of full text for their similarity to natural language queries proposed by users. ANNOD includes common word deletion, word root isolation, query expansion by a thesaurus, and application of a complex empirical matching (ranking) algorithm. The Hepatitis Knowledge Base, the text of a prototype information system, was the file used for testing ANNOD. Responses to a series of users' unrestricted natural language queries were evaluated by three testers. Information needed to answer 85 to 95‰ of the queries was located and displayed in the first few selected paragraphs. It was successful in locating information in both the classified (listed in Table of Contents) and unclassified portions of text. Development of this retrieval system resulted from the complementarity of and interaction between computer science and medical domain expert knowledge. Extension of these techniques to larger knowledge bases is needed to clarify their proper role.

Natural language processing

Abstract: Natural language processing has two primary roles to play in the storage and retrieval of large bodies of information: providing a friendly, easily-learned interface to information retrieval systems, and automatically structuring texts so that their information can be more easily processed and retrieved. This article outlines the organization of a natural language interface for data retrieval (a “question—answering system”) and some of the approaches being taken to text structuring. It closes by describing a few of the research issues in computational linguistics and a possibility for using interactive natural language processing for information acquisition.

Prolog as a simulation language

Abstract: Prolog is a rather new language and is very different from traditional languages. Prolog is favored by the Japanese for their Fifth Generation Computer Systems. The acronym PROLOG is derived from PROgramming in LOGic and emphasizes the derivation of the language from predicate logic. Prolog can be considered as a general purpose very high level language, best suited for general symbol manipulation, intelligent and flexible database handling or problems, where some kind of search is required. Examples of application areas are computer aided design, database and “knowledge-base” management, natural language processing and rapid prototyping.It is the purpose of this paper to demonstrate, how Prolog can be used as a tool in a simulation project.The paper consists of two parts: a survey of the language Prolog and a description of T-Prolog, a Prolog based simulation language, using a process interaction approach.

Semantic Rule Based Text Generation

Abstract: This paper presents a semantically oriented, rule based method for single sentence text generation and discusses its implementation in the Kafka generator. This generator is part of the XCALIBUR natural language interface developed at CMU to provide natural language facilities for a wide range of expert systems and data bases. Kafka takes as input the knowledge representation used in XCALIBUR system and incrementally transforms it first into conceptual dependency graphs and then into English.1

Menu-based natural language understanding

Abstract: Menu-Based Natural Language Understanding is a new approach to building natural language interfaces. It retains the main goals of natural language systems: flexibility, expressive power, learnability and mnemonicity. However, it solves most of the problems inherent to conventional natural language systems. All queries are understood by the system, interface generation is much simpler, and less computing power is required. Many interfaces have been built using the menu-based natural language technology.

Physical Object Representation and Generalization: A Survey of Programs for Semantic-Based Natural Language Processing

Abstract: This article surveys a portion of the field of natural language processing The main areas considered are those dealing with representation schemes, particularly work on physical object representation, and generalization processes driven by natural language understanding The emphasis of this article is on conceptual representation of objects based on the semantic interpretation of natural language input Six programs serve as case studies for guiding the course of the article Within the framework of describing each of these programs, several other programs, ideas, and theories that are relevant to the program in focus are presented

Language-Picture Question-Answering Through Common Semantic Representation And its Application to the World of Weather Report

Abstract: This paper presents some methodologies for constructing systems which can understand both natural languages and pictorial patterns, and describes an application system of the weather report world.

Bridging the gap between AI and IR

Abstract: Information retrieval, in the broadest sense of the term, includes a concern with 'expert' or 'knowledge-based' systems and their potential future successors. It is unlikely that sophisticated systems of this sort can be developed in such a way as to use an entire natural language without the assistance of an advanced, unified theory of language and logic. The need for and probable character of such a theory are discussed.

Expert systems in scientific information exchange

Abstract: The paper presents expert systems as a new generation of information storage and retrieval systems which may consider ably improve the processes of scientific and technical informa tion exchange and dissemination. Essential features of the expert systems with databases containing scientific or technical information have been specified. For databases in which a semantic network is used as a knowledge representation scheme, an idea of database organization has been described with some attention paid to the problem of extracting factual information from the texts of scientific and technical publications. The process of information retrieval from the database of a scien tific or technical information expert system has also been briefly described.

Natural Language for Exert Systems: Comparisons with Database Systems

Abstract: Do natural language database systems still ,~lovide a valuable environment for further work on n~,tural language processing? Are there other sys tems which provide the same hard environment :for testing, but allow us to explore more interesting natural language questions? In order to answer , o to the first question and yes to the second (the position taken by our panel's chair}, there must be an interesting language problem which is more naturally studied in some other system than in the database system.

An investigation into logical optimization of relational query languages

Abstract: On donne une introduction a l'optimisation des langages d'interrogation et on souligne quelques-unes des techniques qui peuvent etre utilisees pour ameliorer la performance d'une base de donnees relationnelle. Discussion sur la complexite de l'optimisation maximale et certaines mesures heuristiques sont donnees pour apporter une meilleure performance aux questions-reponses dans une base de donnees

Using menu-based natural language understanding to avoid problems associated with traditional natural language interfaces to databases (transportable, update, nlmenu)

Abstract: Recently, a new paradigm for natural language interfaces has been developed called "menu-based natural language understanding". An implemented system called the NLMENU system has been designed to explore this approach. The approach has the advantage of guiding the user to use a limited subset of natural language in specifying commands and queries so that all inputs to the NLMENU system are understood. The central thesis of this dissertation is that a guided approach to using limited natural language allows several problems associated with conventional natural language interfaces to databases to be avoided. Three important problems are considered. The first problem involves "value recognition". NLMENU "interaction experts" provide a simple, inexpensive way to recognize, disambiguate and validate database values that occur in user queries or commands and support the user in specifying values in queries at query composition time in a way that conventional natural language systems cannot. The second problem involves allowing end users to automatically generate usable natural language interfaces to database applications. In contrast to conventional natural language interface generators, automatically generated NLMENU interfaces are immediately usable without a long empirical lexicon acquisition phase. The third problem involves showing that the tight control possible in the NLMENU approach can allow expressive database updates while disallowing semantically anomalous ones.

Design And Implementation Of Natural Language Front Ends For Expert Systems

Abstract: McCarthy and Hayesl defined AI in terms of epistemology and heuristics. Research in natural language processing has added a third - a linguistic - dimension to their dichotomy. In this paper, I provide a discussion of general issues, related to natural language interfaces, as well as an overview of GROK2 (Grammatical Representation of Objective Knowledge), a natural language front end for the medical expert system MDX3.

A modal temporal logic for reasoning about changing databases with applications to natural language question answering (artificial intelligence)

Abstract: A database which models a changing world must evolve in correspondence to the world. Previous work on natural language question answering systems for databases has largely ignored the issues which arise when the database is viewed as a dynamic (rather than a static) object. We investigate the question answering behaviors that become possible with the ability to represent and reason about the possible evolution of a database. These behaviors include offering to monitor for a possible future state of the database as an indirect response to a query, and directly answering questions about prior and future possibility. We apply a propositional modal temporal logic that captures possibility and temporality to represent and reason about dynamic databases, and present a sound axiomatization and proof procedure.

Very-high-level programming of knowledge representation schemes

Abstract: This paper proposes building knowledge-based systems using a programming system based on a very-high-level language. It gives an overview of such a programming system, BC, and shows how BC can be used to implement knowledge representation features, providing as examples, automatic maintenance of inverse links and property inheritance. The specification language of BC can be extended to include a knowledge representation language by describing its knowledge representation features. This permits a knowledge-based program and its knowledge base to be written in the same very-high-level language which allows the knowledge to be more efficiently incorporated into the program as well as making the system as a whole easier to understand and extend.

Problems in Question Answering

Abstract: Research in computational question answering has always been conducted with respect to specific tasks. Woods’ LSNLIS program answers questions about its technical knowledge of moon rocks (see Woods 1972); Winograd’s SHRDLU answers questions about the manipulation of blocks on a table (see Winograd 1972); Shortliffe’s MYCIN helps physicians diagnose diseases and prescribe drugs by engaging in question answering dialogues (see Shortliffe 1974); Schank’s SAM reads stories and answers questions about what it reads (see Schank et al. 1975). While all of these programs are concerned with question answering, each one has perceived the problem from a different angle.

Is There Natural Language after Data Bases

Abstract: 1. Why Not Data Base Query? The undisputed favorite application for natural language interfaces has been data base query. Why? The reasons range from the relative simplicity of the task, including shallow semantic processing, to the potential real-world utility of the resultant system. Because of such reasons, the data base query task was an excellent paradigmatic problem for computational linguistics, and for the very same reasons it is now time for the field to abandon its protective cocoon and progress beyond this rather limiting task. But, one may ask, what task shall then become the new paradigmatic problem? Alas, such question presupposes that a single, universally acceptable, syntactically and semantically challenging task exists. I will argue that better progress can be made by diversification and focusing on different theoretically meaningful problems, with some research groups opting to investigate issues arisinq from the development of integrated multi-purpose systems.