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.

Autonomous vehicles and advanced driver assistant systems (ADAS) are receiving notable attention as research fields in both academia and private industry. Some decision-making systems use sets of logical rules to map knowledge of the ego-vehicle and its environment into actions the ego-vehicle should take. However, such rulesets can be difficult to create — for example by manually writing them — due to the complexity of traffic as an operating environment. Furthermore, the building blocks of the rules must be defined. One common solution to this is using an ontology specifically aimed at describing traffic concepts and their hierarchy. These ontologies must have a certain expressive power to enable construction of useful rules. We propose a process of generating sets of explanatory rules for ADAS applications from data using ontology as a base vocabulary and present a ruleset generated as a result of our experiments that is correct for the scope of the experiment.

Knowledge graph embedding aims to embed entities and relations of multi-relational data in low dimensional vector spaces. Knowledge graphs are useful for numerous artificial intelligence (AI) applications. However, they (KGs) are far from completeness and hence KG embedding models have quickly gained massive attention. Nevertheless, the state-of-the-art KG embedding models ignore the category specific projection of entities and the impact of entity types in relational aspect. For example, the entity “Washington” could belong to the person or location category depending on its appearance in a specific relation. In a KG, an entity usually holds many type properties. It leads us to a very interesting question: are all the type properties of an entity are meaningful for a specific relation? In this paper, we propose a KG embedding model TPRC that leverages entity-type properties in the relational context. To show the effectiveness of our model, we apply our idea to the TransE, TransR and TransD. Our approach outperforms other state-of-the-art approaches as TransE, TransD, DistMult and ComplEx. Another, important observation is: introducing entity type properties in the relational context can improve the performances of the original translation distance based models.

Recent studies suggest that learning “how to learn” is important because learners must be self-regulated to take more responsibility for their own learning processes, meta-cognitive control, and other generative learning thoughts and behaviors. The mechanism that enables a learner to self-regulate his/her learning strategies has been actively studied in classroom settings, but has seldom been studied in the area of real-world learning in out-of-school settings (e.g., environmental learning in nature). A feature of real-world learning is that a learner's cognition of the world is updated by his/her behavior to investigate the world, and vice versa. This paper models the mechanism of real-world learning for executing and self-regulating a learner's cognitive and behavioral strategies to self-organize his/her internal knowledge space. Furthermore, this paper proposes multimodal analytics to integrate heterogeneous data resources of the cognitive and behavioral features of real-world learning, to structure and archive the time series of strategies occurring through learner-environment interactions, and to assess how learning should be self-regulated for better understanding of the world. Our analysis showed that (1) intellectual achievements are built by self-regulating learning to chain the execution of cognitive and behavioral strategies, and (2) a clue to predict learning outcomes in the world is analyzing the quantity and frequency of strategies that a learner uses and self-regulates. Assessment based on these findings can encourage a learner to reflect and improve his/her way of learning in the world.

Determining the validity of knowledge triples and filling in the missing entities or relationships in the knowledge graph are the crucial tasks for large-scale knowledge graph completion. So far, the main solutions use machine learning methods to learn the low-dimensional distributed representations of entities and relationships to complete the knowledge graph. Among them, translation models obtain excellent performance. However, the proposed translation models do not adequately consider the indirect relationships among entities, affecting the precision of the representation. Based on the long short-term memory neural network and existing translation models, we propose a multiple-module hybrid neural network model called TransP. By modeling the entity paths and their relationship paths, TransP can effectively excavate the indirect relationships among the entities, and thus, improve the quality of knowledge graph completion tasks. Experimental results show that TransP outperforms state-of-the-art models in the entity prediction task, and achieves the comparable performance with previous models in the relationship prediction task.

The emergency response process is quite complex since there is a wide variety of elements to be evaluated for taking decisions. Uncertainties generated by subjectivity and imprecision affect the safety and effectiveness of actions. The aim of this paper is to develop an onto-logy for emergency response protocols, in particular, to fires in buildings. This developed ontology supports the knowledge sharing, evaluation and review of the protocols used, contributing to the tactical and strategic planning of organizations. The construction of the ontology was based on the methodology Methontology. The domain specification and conceptualization were based in qualitative research, in which were evaluated 131 terms with definitions, of which 85 were approved by specialists. From there, in the Protégé tool, the domain's taxonomy and the axioms were created. The specialists validated the ontology using the assessment by human approach (taxonomy, application and structure). Thus, a sustainable ontology model to the rescue tactical phase was ensured.

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.

The objective of this paper is to recognize and classify the poses of idols in still images on the web. The poses found in Japanese idol photos are often complicated and their classification is highly challenging. Although advances in computer vision research have made huge contributions to image recognition, it is not enough to estimate human poses accurately. We thus propose a method that refines result of human pose estimation by Pose Guide Ontology (PGO) and a set of energy functions. PGO, which we introduce in this paper, contains useful background knowledge, such as semantic hierarchies and constraints related to the positional relationship between body parts. Energy functions compute the right positions of body parts based on knowledge of the human body. Through experiments, we also refine PGO iteratively for further improvement of classification accuracy. We demonstrate pose classification into 8 classes on a dataset containing 400 idol images on the web. Result of experiments shows the efficiency of PGO and the energy functions; the F-measure of classification is 15% higher than the non-refined results. In addition to this, we confirm the validity of the energy functions.

This paper presents the concepts and methodology of knowledge-based information modeling based on Cognitive Science for realizing the autonomous humanoid service robotic arm and hand system HARIS. The HARIS robotic system consists of model-based 3D vision, intelligent scheduler, computerized arm/hand controller, humanoid HARIS arm/hand unit and human interface, and aims to serve the aged and disabled on desk-top object manipulations. The world model, i.e., a shared knowledge base, is introduced to work as a communication channel among the software modules. The task scheduling as well as the 3D-vision is based on Cognitive Science, i.e., a human's way of vision and scheduling is considered in designing the knowledge-based software system. The key idea is to use "words" in describing a scene, scheduling tasks, controlling an arm and hand, and interacting with a human. The world model plays a key role in fusing a variety of distributed functions. The generalized frame-based knowledge engineering environment ZERO++ has been effectively used as a software platform in implementing the system. The experimental system is working within a limited situation successfully. Through the introduction of Cognitive Science-based information modeling we have learned useful hints for realizing human-robot symbiosis, that is our long term goal of the project.

Software Composition is one of the major concerns in component based software development (CBSD). In this paper, we present a formal approach to construct software systems from requirements models using available components. We focus on the knowledge resides in the requirements and the components in order to deal with those heterogeneous concepts. This approach consists of three steps. The first step is selecting adaptable components to the requirements model. The requirements and the components are transformed into the form of Σ algebra, and the component adaptability is evaluated by Σ homomorphism. Rough Set Theory (RST) is used to make carriers of two Σ algebras common, which are derived from the requirements and the components. The second step is identifying the control structure of the requirements. Decision tables are used for representing the knowledge on the requirements, and RST is used to optimize the control structure. The third step is to implement the control structure as glue codes which would perform the components appropriately. This approach mainly focuses on enterprise back-office applications in this paper, however, it can be easily applied to other domains, since it assumes the requirements to be expressed in Colored Petri Nets (CPN), and CPN can express various problem domains other than enterprise back-office applications.

For advanced data-oriented applications in distributed environments, effective information is frequently obtained by integrating or merging various autonomous information sources. There are many problems: how to search information sources, how to resolve their heterogeneity, how to merge or integrate target sources, how to represent information sources with a common protocol, and how to process queries. We have proposed a new language, QUIK, as an extension of a deductive object-oriented database (DOOD) language, QUIXOTE, and extend typical mediator systems. In this paper, we discuss various features of QUIK: programming capabilities as integrating an exchange model and mediator specifications, merging subsumption relations for maintaining consistency, searching alternative information sources by hypothesis generation, and identifying objects.

Conceptual graph formalism is a knowledge representation language in AI based on a graphical form of logic. Although logic is the basis of the conceptual graph theory, there is a strongly felt absence of a formal treatment of conceptual graphs as a logic programming language. In this paper, we develop the notion of a conceptual graph program as a kind of graph-based order-sorted logic program. First, we define the syntax of the conceptual graph program by specifying its major syntactic elements. Then, we develop a kind of model theoretic semantics and fixpoint semantics of the conceptual graph program. Finally, we show that the two types of semantics coincide for the conceptual graph programs.

In this paper, we propose a fuzzy Petri net model for a rule-based decision making system which contains uncertain conditions and vague rules. Using the transformation method introduced in the paper, one can obtain the fuzzy Petri net of the rule-based system. Since the fuzzy Petri net can be represented by some matrices, the algebraic form of a state equation of the fuzzy Petri net is systematically derived. Both forward and backward reasoning are performed by using the state equations. Since the proposed reasoning methods require only simple arithmetic operations under a parallel rule firing scheme, it is possible to perform real-time decision making with applications to control systems and diagnostic systems. The methodology presented is also applicable to classical (nonfuzzy) knowledge base systems if the nonfuzzy system is considered as a special case of a fuzzy system with truth values being equal to the extreme values only. Finally, an illustrative example of a rule-based decision making system is given for automobile engine diagnosis.

The purpose of this paper is to offer a modal logic which enables us symbolic reasoning about data, especially, fuzzy relations. For such a purpose, the present author provided some systems of modal fuzzy logic. As a continuous one of those previous works, a logic based on the graded modalities is proposed. After showing some properties of this logic, the decision procedure for this logic is given in the rectangle method.

Resolving ambiguities in interpreting the user's utterances is one of the most fundamental problems in the development of a question-answering system. The process of disambiguating interpretations requires knowledge and inference functions on an objective task field. This paper describes a framework for understanding conversational language, using the multi-paradigm knowledge representation (frames" and rules") which represents concept hierarchy and causal relationships for an objective field. Knowledge of the objective field is used in the process to interpret input sentences as a model for the objective world. In interpreting sentences, a procedure judges preferences for interpretation candidates by identifying causal relationship with messages in the preceding context, where the causal relationship is used to supplement some shortage of information and to give either an affirmative or a negative explanation to the interpretation. The procedure has been implemented in an experimental question-answering system, whose current task is consultation in operating an electronic device. The experimental results are shown for a concrete problem involving resolving anaphoric references, and characteristics of the knowledge processing system are discussed.