Knowledge-intensive natural language generation

The development of natural language interfaces to artificial intelligence systems is dependent on the representation of knowledge. A major impediment to building such systems has been the difficulty in adding sufficient linguistic and conceptual knowledge to extend and adapt their capabilities. This difficulty has been apparent in systems that perform the task of language production, i.e., the generation of natural language output to satisfy the communicative requirements of a system.A uniform, parsimonious representation of knowledge about language can increase extensibility and efficiency as well as simplify the generation process. The Ace framework applies knowledge representation fundamentals to the task of encoding knowledge about language. Within this framework, linguistic and conceptual knowledge are organized into hierarchies, and structured associations are used to join knowledge structures that are metaphorically related or otherwise used in linguistic expression. These structured associations permit specialized linguistic knowledge to derive partially from more abstract knowledge, facilitating the use of abstractions in generating specialized phrases. A simple generator called KING (Knowledge INtensive Generator) uses an Ace knowledge base to produce utterances from their conceptual representation.     

Definition of a problem-sensitive conceptual modelling language: foundations and application to software engineering

A conceptual modelling language should provide constructors that can be used to represent the conceptualisation of a problem considering the problem domain. However, software engineering has traditionally focused on implementation concepts.This paper considers the appropriate generic conceptualisation theoretical aspects to identify the conceptual elements for which constructors have to be provided in a problem-sensitive conceptual modelling language. These elements match the formal definition of any conceptualisation and are derived from natural language. By looking at these elements, we have defined a conceptual modelling language that has been successfully applied in knowledge engineering and software engineering.     

A note on human factors issues of natural language interaction with database systems

Efforts at constructing natural language computer systems have turned to implementing database query facilities. If the application domain is limited there is renewed hope for the success of natural language interfaces. This paper reviews arguments for and against such facilities, stresses research in human semantic knowledge, and emphasizes controlled psychologically oriented experimentation. The results of recent experiments are reported.     

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.     

An historical overview of natural language processing systems that learn

A fundamental issue in natural language processing is the prerequisite of an enormous quantity of preprogrammed knowledge concerning both the language and the domain under examination. Manual acquisition of this knowledge is tedious and error prone. Development of an automated acquisition process would prove invaluable.This paper references and overviews a range of the systems that have been developed in the domain of machine learning and natural language processing. Each system is categorised into either a symbolic or connectionist paradigm, and has its own characteristics and limitations described.     

Toward formalizing domain modeling semantics in language syntax

Information systems are situated in and are representations of some business or organizational domain. Hence, understanding the application domain is critical to the success of information systems development. To support domain understanding, the application domain is represented in conceptual models. The correctness of conceptual models can affect the development outcome and prevent costly rework during later development stages. This paper proposes a method to restrict the syntax of a modeling language to ensure that only possible configurations of a domain can be modeled, thus increasing the likelihood of creating correct domain models. The proposed method, based on domain ontologies, captures relationships among domain elements via constraints on the language metamodel, thus restricting the set of statements about the domain that can be generated with the language. In effect, this method creates domain specific modeling languages from more generic ones. The method is demonstrated using the Unified Modeling Language (UML). Specifically, it is applied to the subset of UML dealing with object behavior and its applicability is demonstrated on a specific modeling example.     

怎样用物性结构知识解决“网球问题”？

“网球问题”指怎样把racquet(网球拍)、ball(网球)和net(球网)之类具有情境联想关系的词汇概念联系起来、发现它们之间的语义和推理关系。这是一个自然语言处理和相关的语言知识资源建设的世界性难题。该文以求解“网球问题”为目标,对目前比较主流的几种语言词汇和概念知识库系统(包括WordNet、VerbNet、FrameNet、ConceptNet等)进行检讨,指出它们在解决“网球问题”上还都存在一定的局限性,着重分析它们为什么不能解决“网球问题”。进而指出基于生成词库论的名词物性结构知识描写体系可以解决“网球问题”,主张用名词的物性结构知识和相关的句法组合知识来构建一种以名词(实体)为核心的词汇概念网络,以弥补上述几种知识库系统的不足,为自然语言处理提供一种可资参考的词汇概念知识库体系。     

Modeling the user's conceptual knowledge in BGP-MS,a user modeling shell system1

The paper describes the modeling of a user's conceptual knowledge in the general user modeling shell system BGP-MS. On the one hand, BGP-MS is a workbench for the develment of a user model in a particular application domain. It supports the definition of the architecture of the individual user model, and of the architecture and the contents of user stereotypes. A rich representation language for conceptual knowledge, a partition mechanism, and flexible graphics-based interfaces are at the disposal of the user model developer. On the other hand, BGP-MS is a runtime user modeling tool aimed at fulfilling central tasks of a user modeling component in an application system. In this mode, the system offers a functional interface for accessing and updating the model of the current user, as well as basic domain-independent inference mechanisms, support for inferences defined by the developer, and a customizable stereotype management utility. The usefulness of BGP-MS will be demonstrated by illustrating how it can support the user modeling of various recently developed application systems.     

A data management strategy for transportable natural language interfaces

By transportability of a natural language interface (NLI) we mean the ease with which it can be customized to a new domain and database by the database administrator as opposed to a linguistic expert. Next-generation database systems (Genesis, Exodus, Starburst) are expansible to support a variety of applications each of which may use a different knowledge representation strategy. an enhanced architecture for natural language interfaces is presented that takes advantage of expansible next-generation database systems to facilitate transportability. A two-pass strategy for transportability is required within the enhanced architecture. On the first pass the NLI builds a representation space to facilitate its own transportability. On the second pass a transportability solution (viewed as a learning task) occurs in that representation space. © 1995 John Wiley & Sons, Inc.     

A multi-agent conversational system with heterogeneous data sources access

In many of the problems that can be found nowadays, information is scattered across different heterogeneous data sources. Most of the natural language interfaces just focus on a very specific part of the problem (e.g. an interface to a relational database, or an interface to an ontology). However, from the point of view of users, it does not matter where the information is stored, they just want to get the knowledge in an integrated, transparent, efficient, effective, and pleasant way. To solve this problem, this article proposes a generic multi-agent conversational architecture that follows the divide and conquer philosophy and considers two different types of agents. Expert agents are specialized in accessing different knowledge sources, and decision agents coordinate them to provide a coherent final answer to the user. This architecture has been used to design and implement SmartSeller, a specific system which includes a Virtual Assistant to answer general questions and a Bookseller to query a book database. A deep analysis regarding other relevant systems has demonstrated that our proposal provides several improvements at some key features presented along the paper.     

Enhancing information systems management with natural language processing techniques

Natural language and databases are core components of information systems. They are related to each other because they share the same purpose: the conceptualization aspects of the real world in order to deal with them in some way. Natural language processing (NLP) techniques may substantially enhance most phases of the information system lifecycle, starting with requirements analysis, specification and validation, and going up to conflict resolution, result processing and presentation. Furthermore, natural language based query languages and user interfaces facilitate the access to information for anyone and allow for new paradigms in the usage of computerized services. This paper investigates the use of NLP techniques in the design phase of information systems. Then, it reports on data base querying and information retrieval enhanced with NLP.     

面向事实的概念建模方法研究综述

领域概念知识建模是构建信息系统分析的关键技术和任务之一,同时也是知识工程的瓶颈问题,其难点在于如何正确完整地捕捉和验证领域专家的知识。ER和UML等有属性特性的建模方法能够很好地描述领域知识,但却难以让领域专家确认知识的正确性和完整性。面向事实的信息建模(FOM)是一种完全面向自然语言交流的领域概念知识建模方法,是一种理想的概念建模和本体工程辅助工具。简要分析了概念建模过程,比较了不同概念建模方法,介绍了FOM的技术演化过程,从业务规则、动态建模、模型抽象机制、模型转换和工程应用等方面评述了FOM的研究现状和待研究问题。     

Automated Query Formulation Using an Entity–Relationship Conceptual Schema

Significant effort is expended in developing a high-level conceptual schema for a relational database. However, criticalknowledge is often discarded when the conceptual schema is mapped to aset of relation schemas. As a result, designers and users must employsparser logical-level knowledge to access data. Unfortunately, naiveusers do not possess the detailed logical-level knowledge required toformulate queries corresponding to ad hoc requests. Auniversal relation interface can shield users from underlyingdesign details. However, most universal relation systems have beenbased on abstractions not typically used by database designers.Consequently, the usefulness of these interfaces has been limited.This article demonstrates how an Entity-Relationship (ER) conceptualschema can be used by a high-level interface to formulate queriesautomatically. The notion of contextsis introduced to describethe segmentation of an ER conceptual schema into overlapping subgraphsthat correspond to sets of relations that can be joined in a losslessmanner. Given a set of contexts, natural join query formulation isstraightforward. As demonstrated with a case study using theprototype QUICK system, the techniques presented facilitate theconstruction of high-level, intelligent interfaces.     

Advanced human–machine system for intelligent manufacturing

The use of ontologies has gained more and more interest above all for the knowledge management, e.g. the exchange of professional “know-how”, as reported in various previous papers. Under the pressure of a turbulent international market situation enterprises stress the importance of innovation in manufacturing areas. For instance, due to the drastic growing automation degree of manufacturing systems an intuitive interaction form is required, which enables the shop-floor personnel an active participation to the production without specific technical background, as well as to capture and retrieve systematically knowledge contents arising from the interaction process. The following contribution takes this topic into consideration and proposes an innovative ontology- based approach called ontological filtering system (OFS) based on methods and procedures to formalize natural language contents in a systematic way. By means of a so-called ontological network (ON) generic term forms used in the human–machine interaction (HMI) via natural language could be led back to a set of pre-defined terms. Thus, the ON consists, on the one hand, of a large number of generic natural language terms and, on the other hand, of a set of so-called key terms. The generic terms are defined, classified in semantic categories and chained together per semantic relations for a specific use in a particular domain of discourse. The key terms are used to build information on machine level and, therefore, have a formal definition. Through additional syntax roles and application-specific semantic constrains a systematic access and processing of natural language instructions is accomplished computationally. The proposed concepts have been set up and tested within an experimental testbed. The obtained results show a high system performance and encourage the research team to invest further efforts, in order to validate the system operational performances towards its industrial use at shop-floor level. Received: February 2005 / Accepted: January 2006     

Interacting in natural language with artificial systems: The donau project

This paper is intended to propose a new methodological approach to the conception and development of natural language understanding systems. This new contribution is supported by the design, implementation, and experimentation of DONAU: a general purpose domain oriented natural language understanding system developed and presently running at the Milan Polytechnic Artificial Intelligence Project. The system is based on a two level modular architecture intended to overcome the lack of flexibility and generality often pointed out in many existing systems, and to facilitate the exchange of results and actual experiences between different projects. The horizontal level allows an independent and parallel development of the single segments of the system (syntactic analyser, semantic analyser, information extractor, legality controller). The vertical level ensures the possibility of changing (enlarging or redefining) the definition of the semantic domain on which each particular version of the system is oriented and specialized in a simple, incremental, and user-oriented way. In the paper the general architecture of the system and the mode of operation of each segment are illustrated in detail. Linguistic models, knowledge representation, and parsing algorithms are described and illustrated by means of selected examples. Performance evaluations of the system in the application version on data base inquiry are reported and discussed. Promising directions for future research are presented in the conclusions.     

Situating natural language understanding within experience-based design

Building useful systems with an ability to understand "real" natural language input has long been an elusive goal for Artificial Intelligence. Well-known problems such as ambiguity, indirectness, and incompleteness of natural language inputs have thwarted efforts to build natural language interfaces to intelligent systems. In this article, we report on our work on a model of understanding natural language design specifications of physical devices such as simple electrical circuits. Our system, called KA, solves the classical problems of ambiguity, incompleteness and indirectness by exploiting the knowledge and problem-solving processes in the situation of designing simple physical devices. In addition, KA acquires its knowledge structures (apart from a basic ontology of devices) from the results of its problem-solving processes. Thus, KA can be bootstrapped to understand design specifications and user feedback about new devices using the knowledge structures it acquired from similar devices designed previously.In this paper, we report on three investigations in the KA project. Our first investigation demonstrates that KA can resolve ambiguities in design specifications as well as infer unarticulated requirements using the ontology, the knowledge structures, and the problem-solving processes provided by its design situation. The second investigation shows that KA's problem-solving capabilities help ascertain the relevance of indirect design specifications, and identify unspecified relations between detailed requirements. The third investigation demonstrates the extensibility of KA's theory of natural language understanding by showing that KA can interpret user feedback as well as design requirements. Our results demonstrate that situating language understanding in problem solving, such as device design in KA, provides effective solutions to unresolved problems in natural language processing.     

Evaluating the usability of natural language query languages and interfaces to Semantic Web knowledge bases

The need to make the contents of the Semantic Web accessible to end-users becomes increasingly pressing as the amount of information stored in ontology-based knowledge bases steadily increases. Natural language interfaces (NLIs) provide a familiar and convenient means of query access to Semantic Web data for casual end-users. While several studies have shown that NLIs can achieve high retrieval performance as well as domain independence, this paper focuses on usability and investigates if NLIs and natural language query languages are useful from an end-user's point of view. To that end, we introduce four interfaces each allowing a different query language and present a usability study benchmarking these interfaces. The results of the study reveal a clear preference for full natural language query sentences with a limited set of sentence beginnings over keywords or formal query languages. NLIs to ontology-based knowledge bases can, therefore, be considered to be useful for casual or occasional end-users. As such, the overarching contribution is one step towards the theoretical vision of the Semantic Web becoming reality.     

航空术语语义知识库辅助构建方法

语义知识库是自然语言处理任务的基础性资源,广泛应用于语义计算和语义推理等任务。现有的大规模语义知识库基本都是通用型知识库,缺乏特定领域的语义知识。为了弥补这种不足,该文基于HowNet的语义理论体系,提出了一种辅助构建航空术语语义知识库的方法。该方法根据航空术语的特点将辅助构建分成四个关键过程,构建了2 000条术语概念描述(DEF)。最后通过对人工标注的术语间相似度与根据术语DEF计算的术语间相似度结果的对比,验证了该构建方法的有效性。