Developing Conversational Natural Language Interface to a Database

Dutch research on knowledge-based instructional systems: Introduction to the special issue

The need to create mechanisms or systems to acquire, represent and convey knowledge is one of the problems that has been given priority in the passing of the years of research, the need for acquisition has generated the need for more compact models that conserve implicit and explicit knowledge generated within their organizations. In this environment, due to the change that has generated knowledge management, companies recognize the importance of the management of these intangible assets, as a requirement to stay in the market and adapt to organizational and technological changes, each organization must find its own way and recognize that intellectual capacity has become an important factor for the success of organizational development. The aim of this paper is to present the results of a systematic review of the literature by which we identify some acquisition techniques and knowledge representation, that can be replicated in organizations to leverage internal and external knowledge to the organization and achieve advantages sustainable competitive . The results present management techniques related to the culture and values organizational as well as the definition of different types of alliances also identified as expert systems technologies and social tools as useful for the acquisition and representation of knowledge.

Integrating deep learning techniques, particularly language models (LMs), with knowledge representation techniques like ontologies has raised widespread attention, urging the need of a platform that supports both paradigms. Although packages such as OWL API and Jena offer robust support for basic ontology processing features, they lack the capability to transform various types of information within ontologies into formats suitable for downstream deep learning-based applications. Moreover, widely-used ontology APIs are primarily Java-based while deep learning frameworks like PyTorch and Tensorflow are mainly for Python programming. To address the needs, we present DeepOnto, a Python package designed for ontology engineering with deep learning. The package encompasses a core ontology processing module founded on the widely-recognised and reliable OWL API, encapsulating its fundamental features in a more “Pythonic” manner and extending its capabilities to incorporate other essential components including reasoning, verbalisation, normalisation, taxonomy, projection, and more. Building on this module, DeepOnto offers a suite of tools, resources, and algorithms that support various ontology engineering tasks, such as ontology alignment and completion, by harnessing deep learning methods, primarily pre-trained LMs. In this paper, we also demonstrate the practical utility of DeepOnto through two use-cases: the Digital Health Coaching in Samsung Research UK and the Bio-ML track of the Ontology Alignment Evaluation Initiative (OAEI).

Planning and scheduling problems have become a promising area of research in the field of artificial intelligence (AI). In order to provide collision avoidance and enable successful completion of the task, the robot requires sophisticated knowledge about the environment for processing the tasks or methods. Knowledge representation and reasoning (KR & R) techniques provide such a level of knowledge to perceive the task environment. These techniques include description logic (DL) and ontology-based approaches. DL provides low-level knowledge to describe an environment. With advances in KR using ontology, high-level knowledge domain descriptions can be obtained more effectively. Knowledge representation techniques aid in temporal, ontological and spatial reasoning in a modeled environment. In this chapter, low-level KR & R techniques for task planning are summarized.

Rough set based lattice structure for knowledge representation in medical expert systems: Low back pain management case study

Different knowledge representation tasks require different knowledge representation techniques. Agent designers should therefore be able to easily exploit benefits of various knowledge representation technologies in a single agent system.I describe here a modular agent programming language Jazzyk based on the programming framework of Behavioural State Machines (BSM). BSM framework, and thus also Jazzyk, draws a strict distinction between a knowledge representational and a behavioural level of an agent program. It supports a high degree of modularity w.r.t. employed KR technologies, and at the same time provides a clear and concise semantics.

Knowledge representation with SOUL

Based on a detained discussion of system architectures for knowledge based speech understanding and knowledge representation techniques, criteria for both a knowledge representation scheme and system architectures are developed. Upon this background a system is introduced which is organized around a homogenuous knowledge base. Both the knowledge representation language and the content of the knowledge base are described. The knowledge representation language do not only cover declarative but also procedural knowledge. Analysis processes are guided by a flexibel bottom-up top-down strategy. Besides the procedural semantics of the language the A -Algorithm is used for this purpose. Search graph nodes are judged by a vector which reflects knowledge dependent and acoustic scores and which is admissable for the A -Algorithm.

REX: Robotics expert systems building tool

Artificial intelligence can assist in industrial control in many ways, but this paper concentrates on the role of knowledge-based systems in the areas of control, detection and diagnosis of faults, scheduling and planning. The paper argues that the application of knowledge-based techniques can provide a unification of these and other activities, and outlines the requirements of knowledge representation and inference techniques that are needed to make such systems a reality. The advances in hardware, including sensors as well as computers, that will be driven by and in turn stimulate the introduction of the knowledge-based industrial control systems are also considered.

This paper reviews the development and implementation of a number of approximate reasoning models for production planning and control, inventory capacity and spare parts planning and control, hierarchical-multi-objective scheduling and control etc., to improve the effectiveness of managerial decision support systems in integrated AI—OR models. These approximate reasoning models are based on knowledge representation and inference techniques of fuzzy sets and fuzzy logic to capture environmental uncertainties and managerial expertise in terms of flexible natural language expressions. Such computer system models are ‘user friendly’. They do not require precise information. Ordinal scale strength, which is a minimal data characteristic, is sufficient for such model development and implementation. They may be based on expert knowledge obtained either through real-life experiences or a sophisticated OR model analysis.Key wordsfuzzy setsplanningschedulingmanagement

This paper presents an enhancement of the CARESS system—A Constraint Approximative Reasoning System Support—introduced in (Popescu and Roventa, 1994). CARESS is an experimental system with primarily two objectives: (1)knowledge representation and manipulation techniques and to implement them in PROLOG III, and (2) to develop a knowledge programming environment for building expert systems. We discuss here the use of meta-programming, constraint logic programming and approximate reasoning for the design of expert systems It has already been proven that meta-programming and logic programming are powerful techniques for expert system design. Fuzzy logic can be used to model one kind of uncertainty. Constraint logic programming is useful for dealing with the constraints given by operations using fuzzy sets.

Delfi3 is a knowledge engineering environment which integrates a number of advanced knowledge representation and inference techniques such as a semantic net of objects and relations, a knowledge representation language and a backward/forward chaining interpreter for production rules. Delfi3 is a uniform and transparent system.

In this chapter, several knowledge representation and processing techniques based on a symbolic and semantic approach are briefly described. The majority of present-day techniques, like the relational database model or OWL (Web Ontology Language), is based on the symbolic approach and supports the representation and processing of semantically related knowledge. Although these two techniques have found many successful applications, there are certain limitations in their wider use, stemming from the use of naming in explicit description of the meaning of the represented knowledge. To overcome these limitations, the authors propose a technique based on the semantic approach, Hierarchical Semantic Form (HSF), that uses semantic contexts to implicitly define the meaning. This chapter first provides concise information about the two most popular techniques and their limitations, and then proposes a new technique based on semantic approach, which facilitates a large scale processing of semantic knowledge represented in natural language documents.

Developing knowledge management systems is a complicated task since it is necessary to take into account how the knowledge is generated, how it can be distributed in order to reuse it, and other aspects related to the knowledge flows. On the other hand, many technical aspects should also be considered such as what knowledge representation or retrieval technique is going to be used. To find a balance between both aspects is important if we want to develop a successful system. However, developers often focus on technical aspects, giving less importance to knowledge issues. In order to avoid this, we have developed a model to help computer science engineers to develop these kinds of systems. In our proposal we first define a knowledge life cycle model that, according to literature and our experience, ponders all the stages that a knowledge management system should give support to. Later, we describe the technology (software agents) that we recommend to support the activities of each stage. The article explains why we consider that software agents are suitable for this end and how they can work in order to reach their goals. Moreover, a prototype that uses these agents is also described.