Question-answering tasks over structured knowledge (i.e., tables and graphs) require the ability to encode structural information. Traditional pre-trained language models trained on linear-chain natural language cannot be directly applied to encode tables and graphs. The existing methods adopt the pre-trained models in such tasks by flattening structured knowledge into sequences. However, the serialization operation will lead to the loss of the structural information of knowledge. To better employ pre-trained transformers for structured knowledge representation, we propose a novel structure-aware transformer (SATrans) that injects the local-to-global structural information of the knowledge into the mask of the different self-attention layers. Specifically, in the lower self-attention layers, SATrans focus on the local structural information of each knowledge token to learn a more robust representation of it. In the upper self-attention layers, SATrans further injects the global information of the structured knowledge to integrate the information among knowledge tokens. In this way, the SATrans can effectively learn the semantic representation and structural information from the knowledge sequence and the attention mask, respectively. We evaluate SATrans on the table fact verification task and the knowledge base question-answering task. Furthermore, we explore two methods to combine symbolic and linguistic reasoning for these tasks to solve the problem that the pre-trained models lack symbolic reasoning ability. The experiment results reveal that the methods consistently outperform strong baselines on the two benchmarks.

Traditional pipeline methods for task-oriented dialogue systems are designed individually and expensively. Existing memory augmented end-to-end methods directly map the inputs to outputs and achieve promising results. However, the most existing end-to-end solutions store the dialogue history and knowledge base (KB) information in the same memory and represent KB information in the form of KB triples, making the memory reader's reasoning on the memory more difficult, which makes the system difficult to retrieve the correct information from the memory to generate a response. Some methods introduce many manual annotations to strengthen reasoning. To reduce the use of manual annotations, while strengthening reasoning, we propose a hierarchical memory model (HM2Seq) for task-oriented systems. HM2Seq uses a hierarchical memory to separate the dialogue history and KB information into two memories and stores KB in KB rows, then we use memory rows pointer combined with an entity decoder to perform hierarchical reasoning over memory. The experimental results on two publicly available task-oriented dialogue datasets confirm our hypothesis and show the outstanding performance of our HM2Seq by outperforming the baselines.

This paper proposes methods of finding a ranked list of entities for a given query (e.g. “Kennin-ji”, “Tenryu-ji”, or “Kinkaku-ji” for the query “ancient zen buddhist temples in kyoto”) by leveraging different types of modifiers in the query through identifying corresponding properties (e.g. established date and location for the modifiers “ancient” and “kyoto”, respectively). While most major search engines provide the entity search functionality that returns a list of entities based on users' queries, entities are neither presented for a wide variety of search queries, nor in the order that users expect. To enhance the effectiveness of entity search, we propose two entity ranking methods. Our first proposed method is a Web-based entity ranking that directly finds relevant entities from Web search results returned in response to the query as a whole, and propagates the estimated relevance to the other entities. The second proposed method is a property-based entity ranking that ranks entities based on properties corresponding to modifiers in the query. To this end, we propose a novel property identification method that identifies a set of relevant properties based on a Support Vector Machine (SVM) using our seven criteria that are effective for different types of modifiers. The experimental results showed that our proposed property identification method could predict more relevant properties than using each of the criteria separately. Moreover, we achieved the best performance for returning a ranked list of relevant entities when using the combination of the Web-based and property-based entity ranking methods.

This paper presents an ontology-based driving decision making system, which can promptly make safety decisions in real-world driving. Analyzing sensor data for improving autonomous driving safety has become one of the most promising issues in the autonomous vehicles research field. However, representing the sensor data in a machine understandable format for further knowledge processing still remains a challenging problem. In this paper, we introduce ontologies designed for autonomous vehicles and ontology-based knowledge base, which are used for representing knowledge of maps, driving paths, and perceived driving environments. Advanced Driver Assistance Systems (ADAS) are developed to improve safety of autonomous vehicles by accessing to the ontology-based knowledge base. The ontologies can be reused and extended for constructing knowledge base for autonomous vehicles as well as for implementing different types of ADAS such as decision making system.

We present a design of knowledge circulation framework for quality of service (QoS) control of multimedia communication service (MCS). This framework aims to realizing user oriented and resource aware MCS by enabling effective placement of QoS control knowledge on the network. In this paper, we propose a conceptual design of the framework with knowledge-based multiagent system. In this framework, QoS control knowledge is actively circulated by getting on the agents. We implement a prototype of real-time bidirectional MCS (videoconference system) using this framework, and show initial experiment results using it to evaluate the effectiveness of the framework.

We present a design and implementation of a QoS control mechanism in an Adaptive Multimedia Communication System (AMCS) using multiagent-based computing technology. In this paper, we first define functional requirements for AMCS. Subsequently we describe the design and implementation of AMCS with a knowledge-based multiagent framework to fulfill the functional requirements. Moreover we evaluate the adaptability of the prototype systems of AMCS with the operational situations observed in its experiments. From the result of the experiments, we conclude that the multiagent-based design and implementation is reasonable for construction of AMCS.

This paper reports on clich and related mechanisms appearing in a process of human design of software. During studies on human design knowledge, the authors found frequent instance of same pattern of detailing, named clich. In our study, clich is an intermediate level of design knowledge, during a hierarchical detailing step, residing in between simple reuse and creation by micro design rules, which have already been reported. These three kinds of design knowledge are of various types and have different complexities. Discussions on them, focusing on clich type, with procedures of formation of a simple clich skeleton and generation of a clich are given. The studies show a working model of Zipf's principle, and are some trials to reveal a more detail of human designs.

This paper discusses the characteristics of human design knowledge. By studying a number of actual human made designs of excellent designers, the most frequent basic mental operations of a typical human designer have been found. They are: a design rule for hierarchical detailing reported previously, a micro design rule for generating a hierarchical expansion, dictionary operations to build a micro design rule and dictionaries. This study assumes a multiplicity of knowledge based on Zipf's theory, "the principle of least effort. " Zipf's principle may be proved and it becomes possible to understand the fundamental nature of human design.

We propose a query processing method for amalgamated knowledge bases. Our query processing method is an extension of the magic sets technique for query processing in amalgamated knowledge bases, augmented with the capabilities of handling amalgamated atoms. Through rewriting rules in a given amalgamated knowledge base, our method offers the advantages associated with top-down as well as bottom-up evaluation. We discuss how to handle amalgamated atoms, consider how to check whether an amalgamated atom is satisfiable in a fact set and how to extend a fact set by inserting an amalgamated atom. We also give the transformation procedures for amalgamated knowledge databases and show the correctness of our method.

As expert system technology gains wider acceptance in digital system design, the need to build and maintain a large scale knowledge base will assume greater importance. However, how to build a correct and efficient rule base is even a hard part in the knowledge-based system development. In this paper, we develop FARHDL (Frame-And-Rule-based Hardware Description Language) to form a knowledge base. The FARHDL is simple but powerful to specify the hardware requirements and can be directly simulated by PROLOG. Through the knowledge base transformed from FARHDL, a formal method can be developed to design, implement, and validate the digital hardware systems. Furthermore, behavioral properties, anomaly properties, structural properties, and timing properties are applied to analyze the requirements specification. The purposes of those properties are used to detect explicit/implicit incorrect specification clauses and to capture some desired requirements, such as completeness and consistency. Finally, the analysis results can be a useful tool for finding obscure problems in tricky digital system designs and can also aid in the development of formal specifications.

This paper proposes high-speed similitude retrieval schemes for a viewpoint-based similarity discrimination system (VB-SDS) and presents analytical and experimental performance evaluations. The VB-SDS, which contains a huge set of semantic definitions of commonly used words and computes semantic similarity between any two words under a certain viewpoint, promises to be a very important module in analogical and case-based reasoning systems that provide solutions under uncertainty. By computing and comparing similarities for all words contained in the system, the most similar word for a given word can be retrieved under a given viewpoint. However, the time this consumes makes the VB-SDS unsuitable for inference systems. The proposed schemes reduce search space based on the upper bound of a similarity calculation function to increase retrieval speed. An analytical evaluation shows the schemes can achieve a thousand-fold speedup and confirmed through experimental results for a VB-SDS containing about 40,000 words.

In a conventional client-server system using the satellite communications, the responsibility of the system to the client user is considerably degraded by the long transmission time between the satellite and the ground terminal as well as the relatively low data transmission rate in comparison with the ground transmission line as the Ethernet. In this paper, a new client-server control, VEEC, is proposed to solve the problem. As a result of the experimental performance studies, it is clarified that the responsibility in the client is remarkably improved when the pre-fetching mechanism of VEEC works efficiently.

Intelligent Tutoring Systems (ITS) represents a wide class of computer based tutoring systems, designed with an extensive use of the technology of modern Artificial Intelligence. Successful applications of various expert systems and other knowledge based systems of AI gave rise to a new wave of interests to ITS. Yet, many authors conclude that practically valuable achievements of ITS are rather modest despite the relatively long history of attempts to use knowledge based systems for tutoring. It is advocated in this paper that some basic obstacles for designing really successful ITS are due to the lack of well understood and sound models of the education process. The paper proposes to overcome these problems by borrowing the required models from AI and adjacent fields. In particular, the concept of Learning Levels from AI might be very useful both for giving a valuable retrospective analysis of computer based tutoring and for suggestion of some perspective directions in the field of ITS.

This paper proposes a requirement description and elicitation approach for communication services. Requirements are described in natural language, refined with a knowledge base, and converted to a formal language for program generation. A model for communication services is made as a set of three items: terminal state, terminal action and the response of the communication system to the action. This set, in turn, corresponds to natural language syntax that expresses two conditions (terminal state and action) and their result. These conditions and result are expressed as a sequence of simple sentences that describe the relationship between a terminal and a communication system. Thus, by defining such a description style to reflect the features of communication services, it should be possible to achieve both a high level of description and mechanical processing capabilities at the same time. However, requirement descriptions usually include omission and inconsistency. This problem cannot be solved by merely introducing natural language for the descriptions. Knowledge about the target domain of requirements is needed to resolve it. This paper reports on a knowledge base that stores constraints existing between conditions and results in communication services. This knowledge base is shown to be effective in supplementing omissions and resolving inconsistency. This paper also presents a technique for converting the elicited requirements in natural language to descriptions in a formal language that can be used to generate a program.

The concept of flexible system is long being used by many researchers, aiming to solve some particular problem of adaptation. The problem is viewed differently in different situations. In this paper, we first give a set of definitions and specifications to generalize this concept applicable to any system and in particular to communication networks. Through these definitions we will formalize, what are the conditions a system should satisfy to be called as a Flexible Communication System. The rest of the paper we formalize the concepts of flexible information network, and propose an agent oriented architecture that can realize it.

This paper discusses the role of knowledge in document image understanding from the viewpoints of representation, utilization and acquisition. For the representation of knowledge, we propose two models, a layout model and a content model, which represent knowledge about the layout structure and content of a document, respectively. For the utilization of knowledge, we implement layout analysis and content analysis which utilize a layout model and a content model, respectively. The strategy of hypothesis generation and verification is introduced in order to integrate these two kinds of analysis. For the acquisition of knowledge, we propose a method of incremental acquisition of a layout model from a stream of example documents. From the experimental results of document image understanding and knowledge acquisition using 50 samples of visiting cards, we verified the effectiveness of the proposed method.

This paper describes the concepts and methodologies of the INTELLITUTOR system which is an integrated intelligent programming environment for learning programming. INTELLITUTOR attempts to work as a human programming tutor to guide a user, i.e., a student, in writing a computer program, to detect logical errors within it, and to make advices not only for fixing them but also for letting him notice his misunderstandings. The system consists of three major modules, i.e., GUIDE, ALPUS and TUTOR. GUIDE is a guided editor for easy coding, ALPUS is an algorithm-based program understander, and TUTOR is an embedded-intelligent tutoring system for programming education. The ALPUS system can infer user's intentions from buggy codes in addition to detecting logical errors by means of knowledge-based reasoning. ALPUS uses four kinds of programming knowledge: 1) knowledge on algorithms, 2) Knowledge on programming techniques, 3) Knowledge on a programming language, and 4) Knowledge on logical errors. These knowledge are organized in a hierarchical procedure graph (HPG) as a multi-use knowledge base. The knowledge on logical errors was obtained by means of cognitive experiments. The student model is built by means of the results of ALPUS and interactions between a student and the system. Teaching is done based on the student model. Because the ITS subsystem, i.e., TUTOR, is embedded within the intelligent programming environment interactions for creating the student model could be minimized. Although the current system deals with the PASCAL language, most of the knowledge is applicable to those of procedure-oriented programming languages. The INTELLITUTOR system was implemented in the frame-based knowledge engineering environment ZERO and working on a UNIX workstation for system evaluation.

To develop highly reliable switching software efficiently, a more powerful computer-aided verification system is needed. In this paper, we present an object-oriented switching software verification system, focusing on the basic concept and verification method. The system consists of three basic functions: a model of the switching system, a simulation control mechanism, and a verification mechanism. We also give our evaluation of this system.