KNOWLEDGE REPRESENTATION THROUGH COHERENCE SPACES - A Theoretical Framework for the Integration of Knowledge Representations

2009 ◽  
Keyword(s):  
Knowledge Representation ◽  
Theoretical Framework ◽  
Knowledge Representations ◽  
Coherence Spaces

scholarly journals Negative Sampling in Knowledge Representation Learning: A Mini-Review

2020 ◽  
Author(s):  
Jing Qian ◽  
Gangmin Li ◽  
Katie Atkinson ◽  
Yong Yue
Keyword(s):  
Knowledge Representation ◽  
Link Prediction ◽  
Representation Learning ◽  
Cluster Sampling ◽  
Continuous Space ◽  
Knowledge Representations ◽  
Space Efficiency ◽  
Low Dimensional ◽  
Fixed Distribution

Knowledge representation learning (KRL) aims at encoding components of a knowledge graph (KG) into a low-dimensional continuous space, which has brought considerable successes in applying deep learning to graph embedding. Most famous KGs contain only positive instances for space efficiency. Typical KRL techniques, especially translational distance-based models, are trained through discriminating positive and negative samples. Thus, negative sampling is unquestionably a non-trivial step in KG embedding. The quality of generated negative samples can directly influence the performance of final knowledge representations in downstream tasks, such as link prediction and triple classification. This review summarizes current negative sampling methods in KRL and we categorize them into three sorts, fixed distribution-based, generative adversarial net (GAN)-based and cluster sampling. Based on this categorization we discuss the most prevalent existing approaches and their characteristics.

Relational mentalizing after any representation

2021 ◽  
Vol 44 ◽  
Author(s):  
Eliane Deschrijver
Keyword(s):  
Knowledge Representation ◽  
Mental State ◽  
Nonhuman Primate ◽  
Social Conflict ◽  
Conflict Monitoring ◽  
Knowledge Representations ◽  
Representation Of Knowledge

Abstract Autistic, developmental, and nonhuman primate populations fail tasks that are thought to involve attributing beliefs, but not those thought to reflect the representation of knowledge. Instead of knowledge representations being more basic than belief representations, relational mentalizing may explain these observations: The tasks referred to as reflecting “belief” representation, but not the “knowledge” representation tasks, are social conflict designs. They involve mental conflict monitoring after another's mental state is represented – with effects that need to be accounted for.

scholarly journals TermFrame: A Systematic Approach to Karst Terminology

Dela ◽  
2021 ◽  
pp. 149-167
Author(s):  
Špela Vintar ◽  
Uroš Stepišnik
Keyword(s):  
Knowledge Representation ◽  
Domain Knowledge ◽  
Systematic Approach ◽  
Interdisciplinary Approach ◽  
Domain Model ◽  
Knowledge Network ◽  
Data Driven ◽  
Knowledge Representations ◽  
Visual Knowledge ◽  
Data Driven Approach

We describe a systematic and data-driven approach to karst terminology where knowledge from different textual sources is structured into a comprehensive multilingual knowledge representation. The approach is based on a domain model which is constructed in line with the frame-based approach to terminology and the analytical geomorphological method of describing karst phenomena. The domain model serves as a basis for annotating definitions and aggregating the information obtained from different definitions into a knowledge network. We provide examples of visual knowledge representations and demonstrate the advantages of a systematic and interdisciplinary approach to domain knowledge.

scholarly journals Image-embodied Knowledge Representation Learning

2017 ◽  
Author(s):  
Ruobing Xie ◽  
Zhiyuan Liu ◽  
Huanbo Luan ◽  
Maosong Sun
Keyword(s):  
Knowledge Representation ◽  
Visual Information ◽  
Representation Learning ◽  
Learning Model ◽  
Experimental Results ◽  
Knowledge Graph ◽  
Embodied Knowledge ◽  
Knowledge Representations ◽  
Conventional Methods ◽  
Image Representations

Entity images could provide significant visual information for knowledge representation learning. Most conventional methods learn knowledge representations merely from structured triples, ignoring rich visual information extracted from entity images. In this paper, we propose a novel Image-embodied Knowledge Representation Learning model (IKRL), where knowledge representations are learned with both triple facts and images. More specifically, we first construct representations for all images of an entity with a neural image encoder. These image representations are then integrated into an aggregated image-based representation via an attention-based method. We evaluate our IKRL models on knowledge graph completion and triple classification. Experimental results demonstrate that our models outperform all baselines on both tasks, which indicates the significance of visual information for knowledge representations and the capability of our models in learning knowledge representations with images.

A Framework for Hybrid and Analogical Planning

2005 ◽  
pp. 35-89
Author(s):  
Max Garagnani
Keyword(s):  
Knowledge Representation ◽  
Theoretical Framework ◽  
Knowledge Representation And Reasoning ◽  
Domain Description ◽  
Description Languages ◽  
Hybrid Planning

This chapter describes a model and an underlying theoretical framework for hybrid planning. Modern planning domain description languages are based on sentential representations. Sentential formalisms produce problem encodings that often lead the system to carry out large amounts of superfluous operations, causing a loss in performance. This chapter illustrates how techniques from the area of knowledge representation and reasoning (in particular, analogical representations) can be adopted to develop more efficient domain description languages. Although often more efficient, analogical representations are generally less expressive than sentential ones. A framework for planning with hybrid representations is thus proposed, in which sentential and analogical descriptions can be integrated and used interchangeably, thereby overcoming the limitations and exploiting the advantages of both paradigms.

Knowledge Representation and Conversion for Hybrid Expert Systems

1995 ◽  
Author(s):  
Terrence L. Chambers ◽  
Alan R. Parkinson
Keyword(s):  
Knowledge Representation ◽  
Rapid Prototyping ◽  
Expert Systems ◽  
Decision Trees ◽  
Common Knowledge ◽  
Knowledge Engineer ◽  
Knowledge Representations ◽  
Functional Logic ◽  
Decision Tables

Abstract Many different knowledge representations, such as rules and frames, have been proposed for use with engineering expert systems. Every knowledge representation has certain inherent strengths and weaknesses. A knowledge engineer can exploit the advantages, and avoid the pitfalls, of different common knowledge representations if the knowledge can be mapped from one representation to another as needed. This paper derives the mappings between rules, logic diagrams, frames, decision tables and decision trees using the calculus of truth-functional logic. The logical mappings between these representations are illustrated through a simple example, the limitations of the technique are discussed, and the utility of the technique for the rapid-prototyping and validation of engineering expert systems is introduced.

scholarly journals Knowledge Representation and Management: Interest in New Solutions for Ontology Curation

2021 ◽  
Vol 30 (01) ◽  
pp. 185-190
Author(s):  
Ferdinand Dhombres ◽  
Jean Charlet ◽  
Keyword(s):  
Machine Learning ◽  
Electronic Health Records ◽  
Knowledge Representation ◽  
Medical Informatics ◽  
Open Science ◽  
Research Interest ◽  
Health Records ◽  
Knowledge Representations ◽  
Research Areas ◽  
Significant Research

Summary Objective: To select, present and summarize some of the best papers in the field of Knowledge Representation and Management (KRM) published in 2020. Methods: A comprehensive and standardized review of the medical informatics literature was performed to select the most interesting papers of KRM published in 2020, based on PubMed queries. This review was conducted according to the IMIA Yearbook guidelines. Results: Four best papers were selected among 1,175 publications. In contrast with the papers selected last year, the four best papers of 2020 demonstrated a significant focus on methods and tools for ontology curation and design. The usual KRM application domains (bioinformatics, machine learning, and electronic health records) were also represented. Conclusion: In 2020, ontology curation emerges as a significant topic of research interest. Bioinformatics, machine learning, and electronics health records remain significant research areas in the KRM community with various applications. Knowledge representations are key to advance machine learning by providing context and to develop novel bioinformatics metrics. As in 2019, representations serve a great variety of applications across many medical domains, with actionable results and now with growing adhesion to the open science initiative.

scholarly journals DESARROLLO DE COMPETENCIAS EN LAS ÁREAS DE TECNOLOGÍA Y MATEMÁTICAS A TRAVÉS DE MARCOS CONCEPTUALES

2002 ◽  
Author(s):  
Autores Varios
Keyword(s):  
Knowledge Representation ◽  
Technology Education ◽  
Motor Skills ◽  
Instructional Strategy ◽  
Educational Innovation ◽  
Sixth Grade ◽  
Knowledge Representations ◽  
Environmental Support ◽  
Frame System ◽  
Supported Education

This paper summarizes an educational innovation developed with sixth grade studentsin mathematics and technology education. It uses a shell to produce hypertexts togetherwith a knowledge representation schema.When this instructional strategy is introduced, classrooms can be changed to intellectualproduction spaces. The teacher role is focused on monitoring student earningprocesses, environmental support, and advice on conceptual, methodological andtechnical tasks. Students are very oriented to build knowledge representations whichsummit for validation, first of a/l to their partners, next to their teachers, and finally totheir academic communityDesigning hypertexts based on a frame system consistently help the students toimprove cognitive, metacognitive, colaborative and motor skills. This way of designingcomputer supported education environments, which uses know/edge representationschemas consistent with scientific domains, is a constructivistic approach positivelyrelated to meaningful learning

Extensions of Content Analysis in the Creation of Multimodal Knowledge Representations

2018 ◽  
pp. 63-81
Author(s):  
Lesley S. J. Farmer
Keyword(s):  
Content Analysis ◽  
Knowledge Representation ◽  
Design Theory ◽  
Information Design ◽  
Information Architecture ◽  
Knowledge Representations ◽  
Information Behaviors ◽  
Shared Information ◽  
Structuring Knowledge ◽  
Combining Information

Information architecture is the structural design of shared information environments, optimizing users' interaction with that knowledge representation. This chapter explains knowledge representation and information architecture, focusing on comic arts' features for representing and structuring knowledge. Then it details information design theory and information behaviors relative to this format, also noting visual literacy. With this background, an expanded view of content analysis as a research method, combining information design to represent knowledge and information architecture within the context of comic arts, is explained and concretized. The chapter also recommends strategies for addressing knowledge acquisition and communication through effective knowledge representation.

Criteria for Choosing Representation Languages and Control Regimes for Expert Systems

1984 ◽  
Vol 1 (4) ◽  
pp. 2-17 ◽  
Author(s):  
Han Reichgelt ◽  
Frank van Harmelen
Keyword(s):  
Expert System ◽  
Knowledge Representation ◽  
Expert Systems ◽  
Programming Language ◽  
Knowledge Engineering ◽  
Knowledge Representations ◽  
High Level ◽  
And Control ◽  
Representation Formalism ◽  
Control Regime

AbstractShells and high-level programming language environments suffer from a number of shortcomings as knowledge engineering tools. We conclude that a variety of knowledge representation formalisms and a variety of controls regimes are needed. In addition guidelines should be provided about when to choose which knowledge representation formalism and which control regime. The guidelines should be based on properties of the task and the domain of the expert system. In order to arrive at these guidelines we first critically review some of the classifications of expert systems in the literature. We then give our own list of criteria. We test this list applying our criteria to a number of existing expert systems. As a caveat, we have not yet made a systematic attempt at correlating the criteria and different knowledge representations formalisms and control regimes, although we make some preliminary remarks throughout the paper.

Sign in / Sign up

Export Citation Format

Share Document