scispace - formally typeset
Search or ask a question

Showing papers on "Natural language understanding published in 1982"


Journal ArticleDOI
TL;DR: A computer simulation of reading that is strongly driven by eye fixation data from human readers, and which uses a strategy of immediacy of comprehension, attempting to interpret each word as soon as it is encountered, rather than unnecessarily buffering information.

193 citations


Journal ArticleDOI
TL;DR: The overall architecture of the goal oriented parsing system, along with the basic features of the parsing algorithm, are illustrated, based on the new concept of hierarchical parsing and is mainly directed by the semantics of the language.
Abstract: In this paper, a novel approach to natural language understanding, called goal oriented parsing, is presented. Such a model of comprehension is embedded in the more general frame of interpersonal communication and is applied to the person-machine interaction task. It is based on the claim that understanding imperative natural language is strongly dependent both on the goal of the speaker and on the nature of the hearer. This assumption has proved appropriate for the design of effective and robust natural language interfaces to artificial systems. This approach is supported by the development of an experimental project, called NLI, for enquiring in Italian a relational data base. NLI is to date running on a PDP 11/34 computer at the University of Udine. In this paper we illustrate the overall architecture of the system, along with the basic features of the parsing algorithm. This is based on the new concept of hierarchical parsing and is mainly directed by the semantics of the language. The role of clarification dialogue to overcome critical situations is discussed as well. The use of goal oriented parsing in dealing with full query text and anaphora is also exploited. Several meaningful examples are presented. Comparisons with related works are outlined and promising directions deserving further investigation are presented.

177 citations


Proceedings ArticleDOI
16 Jun 1982
TL;DR: In this paper, a rule-based knowledge engineering approach for natural language understanding is presented, where knowledge of various types can be entered and utilized: syntactic and semantic; assertions and rules.
Abstract: This paper describes the results of a preliminary study of a Knowledge Engineering approach to Natural Language Understanding. A computer system is being developed to handle the acquisition, representation, and use of linguistic knowledge. The computer system is rule-based and utilizes a semantic network for knowledge storage and representation. In order to facilitate the interaction between user and system, input of linguistic knowledge and computer responses are in natural language. Knowledge of various types can be entered and utilized: syntactic and semantic; assertions and rules. The inference tracing facility is also being developed as a part of the rule-based system with output in natural language. A detailed example is presented to illustrate the current capabilities and features of the system.

15 citations


Proceedings ArticleDOI
16 Jun 1982
TL;DR: This communication discusses such features as non-standard grammatical rules, hesitations and false starts due to self-correction, systematic errors due to mismatches between the grammar and sentence generator, and uncorrected true errors.
Abstract: If natural language understanding systems are ever to cope with the full range of English language forms, their designers will have to incorporate a number of features of the spoken vernacular language. This communication discusses such features as non-standard grammatical rules, hesitations and false starts due to self-correction, systematic errors due to mismatches between the grammar and sentence generator, and uncorrected true errors.

7 citations


Proceedings ArticleDOI
05 Jul 1982
TL;DR: An algorithm is presented which transforms prevailing similarities of conceptual meanings as denoted by adjacent space points to establish a binary, non-symmetric, and transitive relation between them which allows for the hierarchical reorganization of points as nodes dependent on a head in a binary tree called connotative dependency structure (CDS).
Abstract: Natural language understanding systems make use of language and/or world knowledge bases. One of the salient problems of meaning representation and knowledge structure is the modelling of its acquisition and modification from natural language processing. Based upon the statistical analysis of discourse, a formal representation of vague word meanins is derived which constitutes the lexical structure of the vocabulary employed in the texts as a fragment of the connotative knowledge conveyed in discourse. It consists of a distance-like data structure of linguistically labeled space points whose positions give a prototype-representation of conceptual meanings. On the basis of these semantic space data an algorithm is presented which transforms prevailing similarities of conceptual meanings as denoted by adjacent space points to establish a binary, non-symmetric, and transitive relation between them. This allows for the hierarchical reorganization of points as nodes dependent on a head in a binary tree called connotative dependency structure (CDS). It offers an empirically founded operational approach to determine relevant portions of the space structure constituting semantic dispositions which the priming of a meaning point will trigger with decreasing criteriality. Thus, the CDS allows for the execution of associatively guided search strategies, contents-oriented retrieval operations, and source-dependent processes of analogical inferencing.

7 citations


Proceedings ArticleDOI
05 Jul 1982
TL;DR: A first experimental system including a grammatico-semantic analysis of the input texts and questions, a procedure of inferencing, a search for appropriate answers to individual questions and a synthesis of the answers are being implemented, mainly in the language Q and PL/1.
Abstract: A method of automatic answering of questions in natural language, based only on input texts and a set of rules of inference, is described. A first experimental system including a grammatico-semantic analysis of the input texts and questions, a procedure of inferencing, a search for appropriate answers to individual questions and a synthesis of the answers are being implemented, mainly in the language Q and PL/1. The output of the analysis, the underlying representations of the utterances of the input text, serves as a base of the knowledge representation scheme, on which the inference rules (mapping dependency trees into dependency trees) operate.

5 citations


01 Feb 1982
TL;DR: This chapter describes a series of computer models displaying increasingly integrated functioning of language and memory processes, and the organization of a dynamically changing episodic memory is shown to be important both for its effects on the understanding process, and its ability to make generalizations useful for future understanding.
Abstract: : Research on natural language understanding by computer has shown that the nature and organization of memory plays a central role in the understanding process. This chapter describes a series of computer models displaying increasingly integrated functioning of language and memory processes. The organization of a dynamically changing episodic memory is shown to be important both for its effects on the understanding process, and its ability to make generalizations useful for future understanding. (Author)

5 citations


Journal ArticleDOI
TL;DR: BBN's project in Knowledge Representation for Natural Language Understanding is developing techniques for computer assistance to a decision maker who is collecting information about and making choices in a complex situation by designing a system for natural language control of an intelligent graphics display.
Abstract: BBN's project in Knowledge Representation for Natural Language Understanding is developing techniques for computer assistance to a decision maker who is collecting information about and making choices in a complex situation. In particular, we are designing a system for natural language control of an intelligent graphics display. This system is intended for use in situation assessment and information management. We believe that the decision maker needs an extremely flexible system, capable of manipulating large amounts of data and presenting it on a graphical display in a variety of ways until he feels satisfied that he has a grasp of his situation.

2 citations


Journal ArticleDOI
TL;DR: The general architecture and the fundamental design criteria of a system presently being developed at the University of Udine, aimed at allowing non-professional users, to directly access through natural language the services offered by online data bases, are presented.

2 citations


Proceedings ArticleDOI
05 Jul 1982
TL;DR: This paper has developed a new language understanding system called Japanese Q & A system (JQAS) which was a product of the MISE scheme and emphasized the layered approach to build the software environment as the basis for developing the languageUnderstanding system.
Abstract: This paper deals with a software environment for developing the natural language understanding system. The system called Multi-Layered Software Environment (MLSE) is proposed for providing a designer of a language understanding system with wide varieties of design alternatives in software components which derive from Computational Linguistics. The MLSE is a collection of module packages for building the tools for language understanding system. That is, by integrating the Computational Linguistics methods into the MLSE scheme, we have emphasized the layered approach to build the software environment as the basis for developing the language understanding system. In order to illustrate the strategy of the MLSE scheme, we have discussed the case study for designing Question and Answering system. Based upon this case study, we have developed a new language understanding system called Japanese Q & A system (JQAS) which was a product of the MISE scheme. The MLSE has implemented in variety of LISPs such as Inter-Lisp on DEC-20 and Lisp F3 on IBM370.The JQAS has domain specific Q & A system for computer documentation and explanation system.

1 citations


01 Jan 1982
TL;DR: This chapter contains sections titled: Section Contents, Natural Language Understanding has an Esteemed History, Representation and Frames, Intelligent Computer Coaches, and more.
Abstract: This chapter contains sections titled: Section Contents, Natural Language Understanding has an Esteemed History, Representation and Frames, Intelligent Computer Coaches

Journal ArticleDOI
TL;DR: It is not necessary and it is even not advisable to translate the sentences into an internal representation, so as to keep them as they are, and to interpret them at variable depth.
Abstract: It is not necessary and it is even not advisable to translate the sentences into an internal representation [6]. It is preferable to keep them as they are, and to interpret them at variable depth. This concept consists of 3 aspects [4]: progressive description, multiplicity of inference strategies, and evaluation on demand of partial results.

Journal ArticleDOI
TL;DR: The goal of the project is to add robustness to natural language understanding systems by adding rule-based methods of handling illformed input, which includes both ungrammatical and semantically inappropriate utterances.
Abstract: The goal of our project is to add robustness to natural language understanding systems by adding rule-based methods of handling illformed input [1,2,3]. This includes both ungrammatical and semantically inappropriate utterances. The method being used consists of the following procedure:

Book
01 Dec 1982
TL;DR: The authors have written a parsing program which selects appropriate word and sentence meanings by a parallel process known as activation and inhibition and constructed a general model for the representation of tense and aspect of verbs.
Abstract: During this contract period the authors have: (a) continued investigation of events and actions by means of representation schemes called 'event shape diagrams'; (b) written a parsing program which selects appropriate word and sentence meanings by a parallel process known as activation and inhibition; (c) begun investigation of the point of a story or event by modeling the motivations and emotional behaviors of story characters; (d) started work on combining and translating two machine-readable dictionaries into a lexicon and knowledge base which will form an integral part of our natural language understanding programs; (e) made substantial progress toward a general model for the representation of cognitive relations by comparing English scene and event descriptions with similar descriptions in other languages; (f) constructed a general model for the representation of tense and aspect of verbs; (g) made progress toward the design of an integrated robotics system which accepts English requests, and uses visual and tactile inputs in making decisions and learning new tasks.

Journal ArticleDOI
TL;DR: There are two natural language processing projects in progress at the AI Laboratory of Tartu State University, both of which belong to the broader context of AI and natural language understanding.
Abstract: There are two natural language processing projects in progress at the AI Laboratory of Tartu State University, both of which belong to the broader context of AI and natural language understanding.

Journal ArticleDOI
TL;DR: The field of natural language processing already has quite a tradition in Yugoslavia but research is lacking in AI related areas, such as natural language understanding (NLU) and knowledge representation, so a system named SOVA is developed in order to establish sound software support for such research.
Abstract: The field of natural language processing already has quite a tradition in Yugoslavia but research is lacking in AI related areas, such as natural language understanding (NLU) and knowledge representation. In order to establish sound software support for such research we have been developing a system named SOVA.