数据库自然语言接口研究

使用自然语言对数据库进行操作,有利于数据库技术的进一步推广应用。本文首先对语音识别的主要技术隐马尔可夫模型进行了综述,对数据库操作的词法和语义进行了研究,分析给出了基本的操作语句框架。     

基于数据库查询的自然语言接口研究

语音识别技术是近年来信息领域重要的科技发展技术之一.作为一门交叉学科,语音识别正逐步成为信息技术中人机接口的关键技术.探讨了为数据库查询提供自然语言接口的可能性,介绍了图书资料查询系统中语音识别的基本框架,并详细描述了采用微软Speech SDK技术实现图书资料查询的详细过程.给出了查询流程,基于状态转换图的词法分析和语法分析方法,将疑问句转换成SQL查询语句的方法,以及由查询结果生成答句的方法.     

A general-purpose natural language interface to an operating system

One of the most difficult tasks facing new computer users is the management of data and programs through an operating system (OS) interface. Both command languages and graphical interfaces can impede a user unfamiliar with the terminology and organizational techniques of modern file management systems. Various attempts have been made in recent years to develop systems that will enable users to interact with the computer in natural language. By simplifying the form of user input to an OS, such interfaces allow the user to concentrate on file management tasks rather than on the means of expressing OS-specific instructions. The Informational Network for a Natural Talking (INFANT) System was originally developed as a conversational system for communication at the level of a small child. It has since been adapted for use as a general-purpose English language interface for standard OS file management operations. The INFANT System reduces an input sentence to a hierarchy of standardized propositional forms, which are mapped through a propositional knowledge base and a compositional semantics process into a high-level representation of meaning. Its effectiveness as a working natural language interface has been verified in a pair of experiments performed in a college computer lab. © 1996 John Wiley & Sons, Inc.     

基于复述的中文自然语言接口

针对传统以句法分析为主的数据库自然语言接口系统识别用户语义准确率不高,且需要大量人工标注训练语料的问题,提出了一种基于复述的中文自然语言接口(NLIDB)实现方法。首先提取用户语句中表征数据库实体词,建立候选树集及对应的形式化自然语言表达;其次由网络问答语料训练得到的复述分类器筛选出语义最相近的表达;最后将相应的候选树转换为结构化查询语句(SQL)。实验表明该方法在美国地理问答语料(GeoQueries880)、餐饮问答语料(RestQueries250)上的F1值分别达到83.4%、90%,均优于句法分析方法。通过对比实验结果发现基于复述方法的数据库自然语言接口系统能更好地处理用户与数据库的语义鸿沟问题。     

A natural language interface to a clinical data base management system

Communication with a clinical data base in a natural language has been viewed for years as a desired objective to improve clinical decision making. This paper describes an exploratory system to interface medical personnel to an existing data base management system without a need for a formal query language. The methods involve contextual and syntactic analysis with emphasis on semantic interpretation of limited medical terminology in the area of kidney failure therapy. System testing by physicians resulted in modifications and improvements. A limited system of graphical displays and statistical analyses was integrated into the system to help physicians in the interpretations of clinical trends and observations.     

A relational tsetlin machine with applications to natural language understanding

Journal of Intelligent Information Systems - Tsetlin machines (TMs) are a pattern recognition approach that uses finite state machines for learning and propositional logic to represent patterns. In...     

Using a natural language interface with casual users

Although there is much controversy about the merits of natural language interfaces, little empirical research has been conducted on the use of natural language interfaces for database access, especially for casual users. In this work casual users were observed while interacting with a real-life database using a natural language interface, Intellect.Results show that natural language is an efficient and powerful means for expressing requests. This is especially true for users with a good knowledge of the database contents regardless of training or previous experience with computers. Users generally have a positive attitude towards natural language. The majority of errors users make are directly related to restrictions in the vocabulary. However, feedback helps users understand the language limitations and learn how to avoid or recover from errors. Natural language processing technology is developed enough to handle the limited domain of discourse associated with a database; it is simple enough to support casual users with a general knowledge of the database contents; and it is flexible enough to assist problem-solving behaviour.     

Programmable applications: exploring the potential for language/interface symbiosis

Abstract

Programmable applications are software systems that seek to combine the learnability and accessibility of direct manipulation interfaces with the expressive power and range of programming languages. In this paper we explore techniques for creatively integrating language and interface constructs within programmable applications. Using SchemePaint—a programmable graphics application—as a source of examples, we demonstrate how an interface and language can combine symbolically and thereby provide powerful modes of expression within applications.     

Programmable applications: exploring the potential for language/interface symbiosis

Programmable applications are software systems that seek to combine the learnability and accessibility of direct manipulation interfaces with the expressive power and range of programming languages. In this paper we explore techniques for creatively integrating language and interface constructs within programmable applications. Using SchemePaint—a programmable graphics application—as a source of examples, we demonstrate how an interface and language can combine symbolically and thereby provide powerful modes of expression within applications.     

Pragmatic modeling: toward a robust natural language interface

One of the most important ways in which an information-provider can assimilate an information-seeking dialogue is by inferring the underlying task-related plan motivating the information-seeker's queries. This paper presents a strategy for hypothesizing and tracking the changing task-level goals of an information-seeker and building a model of his task-related plan as the dialogue progresses.
Naturally occurring utterances are often imperfect. The information-provider often appears to use acquired knowledge about the information-seeker's underlying task-related plan to remedy many of the information-seeker's faulty utterances and enable the dialogue to continue without interruption. This paper presents a strategy for understanding one kind of defective utterance. Our approach relies on the information-seeker's inferred task-related plan as the primary mechanism for suggesting how an utterance should be understood, thereby considering only interpretations that are relevant to what the information-seeker is trying to accomplish. If multiple interpretations are suggested, relevance to the current focus of attention in the dialogue and similarity to the information-seeker's actual utterance are used to select the interpretation that is most likely to represent his intended meaning or satisfy his needs.     

User‐interface design heuristics for developing usable industrial hypermedia applications

Shop floor operators urgently need help to cope with the pressures of the present manufacturing context. One proposed solution is industrial hypermedia applications (IHA). A review of published papers on IHAs has shown that while the potential benefits of such applications, if accepted and used by operators, are well documented, user‐interface design aspects are not. In other words, the rationale used for the user‐interface design is not explained. This article fills the gap by drawing on human–computer interaction and hypermedia literature to present user‐interface design guidelines or heuristics. The latter were incorporated in 2 IHAs developed for this study. Shop floor operators empirically assessed the IHAs through usability trials held in the workplace and provided data on their perceptions of the IHA's ease of use. The findings show that the 7 design heuristics contributed to the usability of the IHAs. However, developers should not apply the design heuristics in isolation but should also elicit user characteristics and task domain. © 2002 Wiley Periodicals, Inc.     

Algebraic semantics for natural language: some philosophy, some applications

Information processing, when performed by an intelligent agent, draws on a wide array of knowledge sources. Among them are world knowledge, situation knowledge, conceptual knowledge and linguistic knowledge. The focus in this paper will be on the semantic knowledge which is part of the general linguistic competence of any speaker of a natural language (NL).In particular, this knowledge contains ways of organizing the linguistic ontology, i.e. the collection of heterogeneous entities that make up the domain of discourse. The representation language that is proposed here to model this knowledge stresses the structural properties of the ontology. This approach has been persued under the name of algebraic semantics.The paper starts out by explaining the term "algebraic semantics" as it is used in logic. Two senses of "algebraic" are distinguished that are called here "conceptual" and "structural". These two senses of the algebraic method are then applied to NL semantics. The conceptual part is realized by the method of structuring the domains of linguistic ontology in various ways. Thus plural entities are recognized along with mass entities and events. The common outlook here is mereological or lattice-theoretical. Some applications to the study of plurals are given that are to show the usefulness of the algebraic approach. Finally, the ontology of plurals is addressed, and comments are made on some relevant discussion of mereology in recent philosophical work. In sum, it is contended that the algebraic perspective while being of interest in semantics and philosophy proper, also fits both the spirit and the practice of much work that has been done in the Artificial Intelligence (AI) field of knowledge representation.     

Experience on knowledge-based software engineering: A logic-based requirements language and its industrial applications

A formal requirements specification language plays an important role in software development. Not only can such language be used for stating requirements specification, but also can be used in many phases of software development life cycle. The FRORL project started from constructing a language with a solid logical foundation and further expanded to research in verification, validation, requirements analysis, debugging, and transformation. Research in this project aided in some industrial applications in which a code generation tool produced software for embedded systems. This article reports the experiences gained from this project and states the value of research in knowledge-based software engineering.     

User interface design for cooperating agents in industrial process supervision and control applications

Computer systems based on cooperating agent architectures are currently introduced in industrial process supervision and control applications as operator support systems in tasks such as fault diagnosis, system restoration etc. Cooperating agents are relevant to these applications since they involve a high degree of physical distribution, the operators' decisions are often based on multiple conflicting views which can be moderated by the cooperating agents, and the domains are complex with high degree of modularity.In the frame of the research project ARCHON, a multi-agent system architecture has been defined in order to be used in industrial process supervision and control applications. An issue of high importance in this context is the interaction with the human operator and the design of a user interface which supports this interaction. The impact of multi-agent architectures on the user interface design of industrial process supervision and control systems is the subject of this paper. An example of an interface designed for a multi-agent system in the area of electrical network supervision is provided.