Showing papers on "Question answering published in 1983"

Conceptual Structures: Information Processing in Mind and Machine

Abstract: It sounds good when knowing the conceptual structures information processing in mind and machine in this website. This is one of the books that many people looking for. In the past, many people ask about this book as their favourite book to read and collect. And now, we present hat you need quickly. It seems to be so happy to offer you this famous book. It will not become a unity of the way for you to get amazing benefits at all. But, it will serve something that will let you get the best time and moment to spend for reading the book.

Design of a knowledge-based report generator

Abstract: Knowledge-Based Report Generation is a technique for automatically generating natural language reports from computer databases. It is so named because it applies knowledge-based expert systems software to the problem of text generation. The first application of the technique, a system for generating natural language stock reports from a daily stock quotes database, is partially implemented. Three fundamental principles of the technique are its use of domain-specific semantic and linguistic knowledge, its use of macro-level semantic and linguistic constructs (such as whole messages, a phrasal lexicon, and a sentence-combining grammar), and its production system approach to knowledge representation.

A Field Evaluation of Natural Language for Data Retrieval

Abstract: Although a large number of natural language database interfaceshave been developed, there have been few empirical studies of theirpractical usefulness. This paper presents the design and results of afield evaluation of a natural language system - NLS - used for dataretrieval .A balanced, multifactorial design comparing NLS with a referenceretrieval language, SQL, is described. The data are analyzed on twolevels: work task (n=87) and query (n=1081). SQL performed betterthan NLS on a variety of measures, but NLS required less effort touse. Subjects performed much poorer than expected based on theresults of laboratory studies. This finding is attributed to thecomplexity of the field setting and to optimism in grading laboratoryexperiments.The methodology developed for studying computer languages in realwork settings was successful in consistently measuring differences intreatments over a variety of conditions.

An examination of fifth- and eighth-grade children's question-answering behavior: an instructional study in metacognition

Abstract: While it may be obvious that one's ability to answer a question is dependent upon the knowledge one possesses relative to the question's topic, less obvious, but equally important, is one's ability to access appro- priate information sources in search of a correct answer. The purpose of this study was to examine the effects of a ten-week program designed to heighten fifth- and eighth-grade students' awareness of information explicitly stated in text, information implied by text, and information found only in the individual's knowledge base. In addition, the relative useful- ness of prompting students to think of these three relationships between questions and sources of information was examined. Results indicated that while the training program was effective at both the fifth and eighth grades, the eighth-grade students benefitted as much from a 10-minute orientation to the concepts. Prompting students to use their knowledge of question- answer relationships was helpful in the fifth grade, but disruptive in the eighth. The use of questions represents one of the primary means by which we are able to assess children's comprehension of what they read. It seems A version of the paper was presented at the National Reading Conference, Clearwater, FL, December 1982. We would like to thank Joe Byers for his invaluable help in the analysis of the data, as well as the students and faculty of Buena Vista and Butler Elementary Schools, and Butler and Union Middle Schools of the Jordon School District in Utah for their partici- pation in the study.

Building Usable Menu-Based Natural Language Interfaces To Databases

Abstract: Natural language interfaces to databases are not in couunon use today for two main reasons: they are difficult to use and they are expensive to build and maintain. This paper presents a functional overview of a new kind of natural language interface that goes far in overcoming both of these problems. The “ease-of-use” problem is solved by wedding a menu-based interaction technique to a traditional semantic graaauar-driven natural language system. Using this approach, all user queries are “understood” by the system. The “creation and maintenance problem” is solved by designing a core grannnar with parameters supplied by the data dictionary and then automatically generating semantic graumars covering some selected subpart of the user’s data. Automatically generated natural language interfaces offer the user an attractive way to group semantically related tables together, to model a user’s access rights, and to model a user's view of supported joins paths in a database.

Automatic Natural Language Parsing

Abstract: This collection of papers on automatic natural language parsing examines research and development in language processing over the past decade. It focuses on current trends toward a phrase structure grammar and deterministic parsing.

Usable natural language interfaces through menu-based natural language understanding

Abstract: Conventional natural language interfaces suffer from several ease-of-use problems. They require a user to type and to formulate questions in a way that the system can understand. They have high failure rates which often frustrate users, and users often do not use features of the systems because they are unaware of them or don't trust them. In addition, conventional natural language systems are expensive to build and require large amounts of storage to use. This paper describes a new approach to natural language interfaces called menu-based natural language understanding. This new approach solves the problems listed above. The paper compares the menu-based natural language approach to conventional natural language interfaces and to other forms of interface and discusses the advantages and limitations of this new approach.

Knowledge-Based Report Generation: a technique for automatically generating natural language reports from databases

Abstract: Knowledge-Based Report Generation is a technique for automatically generating natural language summaries from databases. It is so named because it applies the tools of knowledge-based expert systems design to the problem of text generation. The technique is currently being applied to the design of an automatic natural language stock report generator. Examples drawn from the implementation of the stock report generator are used to describe the components of a knowledge-based report generator.

Researcher: an overview

Abstract: Described in this paper is a computer system, RESEARCHER, being developed at Columbia that reads natural language text in the form of patent abstracts and creates a permanent long-term memory based on concepts generalized from these texts, forming an intelligent information system. This paper is intended to give an overview of RESEARCHER. We will describe briefly the four main areas dealt with in the design of RESEARCHER: 1) knowledge representation, where a canonical scheme for representing physical objects has been developed, 2) memory-based text processing, 3) generalization and generalization-based memory organization that treats concept formation as an integral part of understanding, and 4) generalization-based question answering.

Indexing and retrieval strategies for natural language fact retrieval

Abstract: Researchers in artificial intelligence have recently become interested in natural language fact retrieval; currently, their research is at a point where it can begin contributing to the field of Information Retrieval. In this paper, strategies for a natural language fact retrieval system are mapped out, and approaches to many of the organization and retrieval problems are presented. The CYRUS system, which keeps track of important people and is queried in English, is presented and used to illustrate those solutions.

The Effect of Prior Knowledge on the Question Answering of Good and Poor Readers

Abstract: The purpose of this investigation was to compare the question answering of good and poor readers when their prior knowledge for the answers to questions was determined before reading to be accurate, inac- curate, incomplete, or missing. Fifty-six fifth-grade students with equiva- lent I.Q.'s, but varying in reading ability and extent of general prior knowledge for the passage topics, participated in the study. Subjects read an expository passage written on their approximate instructional reading level. The results indicated that poor readers did not use prior knowledge to the same extent as did good readers. This was especially true when students were learning new information. The results also suggest that poor readers have difficulty answering text implicit questions even if they pos- sess adequate prior knowledge for passage topics.

Knowledge based question answering

Abstract: The natural language database query system incorporated in the KNOBS interactive planning system comprises a dictionary driven parser, APE-II, and script interpreter which yield a conceptual dependency conceptualization as a representation of the meaning of user input. A conceptualization pattern matching production system then determines and executes a procedure for extracting the desired information from the database. In contrast to syntax driven Q-A systems, e.g., those based on ATN parsers, APE-II is driven bottom-up by expectations associated with word meanings. The processing of a query is based on the contents of several knowledge sources including the dictionary entries (partial conceptualizations and their expectations), frames representing conceptual dependency primitives, scripts which contain stereotypical knowledge about planning tasks used to infer states enabling or resulting from actions, and two production system rule bases for the inference of implicit case fillers, and for determining the responsive database search. The goals of this approach, all of which are currently at least partially achieved, include utilizing similar representations for questions with similar meanings but widely varying surface structures, developing a powerful mechanism for the disambiguation of words with multiple meanings and the determination of pronoun referents, answering questions which require inferences to be understood, and interpreting ellipses and ungrammatical utterances.

Generation in a natural language interface

Abstract: The PHRED (PHR asal English Diction) generator produces the natural language output of Berkeley's UNIX Consultant system (UC). The generator shares its knowledge base with the language analyzer PHRAN (PHRasal ANalyser). The parser and generator, together a component of UC's user interface, draw from a database of pattern-concept pairs where the basic unit of the linguistic patterns is the phrase. Both are designed to provide multilingual capabilities, to facilitate linguistic paraphrases, and to be adaptable to the individual user's vocabulary and knowledge. The generator affords extensibility,simplicity, and processing speed while performing the task of producing natural language utterances from conceptual representations using a large knowledge base. This paper describes the implementation of the phrasal generator and discusses the role of generation in a user-friendly natural language interface.

Ir-nli : an expert natural language interface to online data bases

Abstract: Constructing natural language interfaces to computer systems often requires achievment of advanced reasoning and expert capabilities in addition to basic natural language understanding. In this paper the above issues are faced in the frame of an actual application concerning the design of a natural language interface for the access to online information retrieval systems. After a short discussion of the peculiarities of this application, which requires both natural language understanding and reasoning capabilities, the general architecture and fundamental design criteria of a system presently being developed at the University of Udine are then presented. The system, named IR-NLI, is aimed at allowing non-technical users to directly access through natural language the services offered by online data bases. Attention is later focused on the basic functions of IR-NLI, namely, understanding and dialogue, strategy generation, and reasoning. Knowledge represenetation methods and algorithms adopted are also illustarted. A short example of interaction with IR-NLI is presented. Perspectives and directions for future research are also discussed.

A Model for Integrated Information Systems

Abstract: The application of the traditional data base models in the important areas of document retrieval and office information systems has not yet yielded great evidence of success Here we present an alternative model based on array theory This model appears to be better suited toward other types of information system,while at the same time, it is still applicable to conventional data base operations An outline of the model is presented, a description of a suitable query language is given and some implementation issues are discussed

A tutorial on techniques and applications for natural language processing

Abstract: Natural language communication with computers has long been a major goal of Artificial Intelligence both for what it can tell us about intelligence in general and for its practical utility - data bases, software packages, and Al-based expert systems all require flexible interfaces to a growing community of users who are not able or do not wish to communicate with computers in formal, artificial command languages Whereas many of the fundamental problems of general natural language processing (NLP) by machine remain to be solved, the area has matured in recent years to the point where practical natural language interfaces to software systems can be constructed in many restricted, but nevertheless useful, circumstances This tutorial is intended to survey the current state of applied natural language processing by presenting computationally effective NLP techniques, by discussing the range of capabilities these techniques provide for NLP systems, an by discussing their current limitations Following the introduction, this document is divided into two major sections: the first on language recognition strategies at the single sentence level, and the second on language processing issues that arise during interactive dialogues In both cases, we concentrate on those aspects of the problem appropriate for interactive natural languagemore » interfaces, but relate the techniques and systems discussed to more general work on natural language, independent of application domain« less

Q-TRANS: query translation into English

Abstract: Q-TRANS, which stands for Query-TRANSlation System, translates formal database queries into English to enhance the usability of both natural and formal language database access systems. Q-TRANS is designed for the database query language SQL, whose query expressions serve as an abstract representation from which an English paraphrase is generated. Q-TRANS is also intended to be part of the Transformational Question Answering System (TQA system), which provides a natural language interface for database query, analyzing and ultimately translating the English queries into SQL expressions. The concepts and methods used in Q-TRANS to arrive at a query translation are, however, independent from the TQA system except for compatibility of lexical and grammatical coverage of the paraphrar.es produced. The paraphrases generated are true translations of the SQL expressions which are the input to Q-TRANS and serve in a sense as deep structures that get mapped into English imperatives. The grammatical English structures Q-TRANS produces obey somewhat conflicting constraints in that they preserve as much of the SQL structure as necessary to reflect the internal logic to the user, and at the same time represent as natural English sentences as possible.

Isolating domain dependencies in natural language interfaces

Abstract: Isolating the domain-dependent information within a large natural language system offers the general advantages of modular design and greatly enhances the portability of the system to new domains. We have explored the problem of isolating the domain dependencies within two large natural language systems, one for generating a tabular data base from text ("information formatting"), the other for retrieving information from a data base. We describe the domain information schema which is used to capture the domain-specific information, and indicate how this information is used throughout the two systems.

Epistemology and the theory of problem solving

Abstract: Problem solving has recently become a central topic both in the philosophy of science and in cognitive science. This paper integrates approaches to problem solving from these two disciplines and discusses the epistemological consequences of such an integration. The paper first analyzes problem solving as getting a true answer to a question. It then explores some stages of cognitive activity relevant to question answering that have been delineated by historians and philosophers of science and by cognitive psychologists and artificial intelligencers. The traditional opposition between discovery and justification is challenged. It is suggested that epistemology may be conceptualized, in part, as the critical assessment of problem-solving strategies.

Some research problems in automatic information retrieval

Abstract: Information retrieval components are currently incorporated in several types of information systems, including bibliographic retrieval systems, data base management systems and question-answering systems. Some of the problems arising in the real-time environment in which these systems operate are briefly discussed. Certain recent advances in information retrieval research are then mentioned, including the formulation of new probabilistic retrieval models, and the development of automatic document analysis and Boolean query processing techniques.

Logic and Natural Language

Abstract: Logic is that branch of knowledge concerned with truth and inference-that is, with determining the conditions under which a proposition is true or one proposition may be inferred from others. Such knowledge is essential for communication since most of our beliefs about the world come, not from direct contact with it, but from what others tell us and from what we in turn tell others. Therefore, it is not surprising that logic underlies a wide range of current research on natural language interactions with machines, including parsing,1 semantic interpretation,2 and reasoning about an agent's goals in order to understand his utterances.3 However, not just first-order logic but also more powerful-or at least very different-forms of logic are being used in understanding and generating natural language. This article discusses three of these forms: default logic, used in computing presuppositions; modal logic, for planning utterances to enlist help; and temporal logic, for offering competent database monitors and correcting certain user misconceptions. What I hope the reader gains from this discussion is a sense of logic's preeminence in providing \"natural\" natural-language interactions with machines. Understanding and generating language are exercises in reasoning. For reasoning, logic is our best tool.

Towards knowledge acquisition from natural language documents: automatic model construction from hardware manual

Abstract: In this paper, we explore automatic model construction by analyzing natural language documents. The extracted model will be utilized by a CAD system. A system called hmU, in the course of development, is designed to allow knowledge on very complex hardware module like LSI or VLSI to be incorporated into its knowledge base. The acquired knowledge will be utilized for helping human designer understand the component from various levels of abstraction. The focus of this paper is attentioned more to issues on knowledge representation and model inference than that on natural language analysis. Hierarchical model is employed. In particular, cause-effect representation is used to make it clear how actions of each module and events are related to each other. A brief description is given to illustrate our approach.

Natural Language for Database Queries: A Laboratory Study

Abstract: Are natural language systems for database queries meetingtheir goals? And, are these goals appropriate? The recentlycompleted Advanced Language Project at New York Universitycombined a field experiment with two laboratory studies toexamine these issues by comparing performance between subjectsusing the formal database language SQL and subjects using theprototype natural language system, USL. This paper describesthe design and results of the larger laboratory experiment.The results presented offer some promise for the usability ofnatural language under certain conditions.

KL-Conc: a language for interacting with Si-Nets

Abstract: This paper introduces KL-Conc language, a Knowledge Representation Language based on KL-Magma, which is a version of KL-ONE. The aim of KL-Conc is to simulate conceptual operations underlying natural language. Relationships and differences between KL-Conc and KL-ONE are also discussed.