Integrating Knowledge Representation and Reasoning in Machine Learning

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: closed (10 December 2021) | Viewed by 18635

Special Issue Editors

School of Business, FHNW University of Applied Sciences and Arts Northwestern Switzerland, Olten, Switzerland
Interests: artificial intelligence; hybrid intelligence combining AI and human; enterprise modelling; alignment of business and IT; digitalization of business processes and knowledge work
Special Issues, Collections and Topics in MDPI journals
School of Business, FHNW University of Applied Sciences and Arts, 4600 Olten, Switzerland
Interests: conversational AI, case-based reasoning; machine learning; knowledge representation and reasoning; process digitalization and automation

Special Issue Information

Dear Colleagues,

Artificial Intelligence can be regarded as the transfer of human thinking and learning to a computer such that it can intelligently solve challenging problems. Human intelligence combines rational reasoning with processing large amounts of data. In its early years, Artificial Intelligence focused on rational thinking resulting in expert systems, which have a knowledge base and an inference engine. It turned out that these systems are hard to maintain and to keep up to date. Furthermore, there are applications which need knowledge that cannot be expressed in symbol-processing systems. In recent years, machine learning has helped to solve complex tasks based on real-world data. It is suitable for building AI systems when knowledge is not known, or knowledge is tacit. Deep learning allows for building systems that learn from vast amounts of data.

While machine learning, particularly deep learning, can master data-intensive learning tasks, there are still some challenges, many of them related to a lack of knowledge. Deep learning systems search for correlations in data rather than meaning. In the learning phase, they can hardly distinguish between meaningful and irrelevant indicators. In the application phase, they are not aware of their boundaries. Moreover, many business cases and real-life scenarios require background knowledge and explanations of results and behavior. Application domains, in which safety and control are fundamental, demand symbolic approaches that can adequately complement machine learning. In medicine, for instance, physicians will likely overrule suggestions if there is no adequate explanation. Furthermore, application areas such as banking, insurance, and life science are highly regulated and require compliance with law and regulations.

This Special Issue collects research work combining the strength of machine learning and knowledge-based systems. Because of their complementary strengths and weaknesses, there is an ongoing demand to integrate knowledge engineering and machine learning for complex scenarios.

Knowledge engineering and knowledge-based systems, which make expert knowledge explicit and accessible, are often based on logic and can explain their conclusions. These systems typically require a higher initial effort during development than systems that use machine learning approaches. Machine learning allows building applications where knowledge cannot be made explicit. Symbolic machine learning and ontology learning approaches are promising for reducing the effort of knowledge engineering.

Prof. Dr. Knut Hinkelmann
Dr. Andreas Martin
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • machine learning
  • knowledge-based systems
  • rule-based systems
  • expert systems
  • ontology
  • deep learning
  • neural network
  • knowledge engineering

Published Papers (7 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

17 pages, 3249 KiB  
Article
On the Track to Application Architectures in Public Transport Service Companies
by Stephan Jüngling, Ilir Fetai, André Rogger, David Morandi and Martin Peraic
Appl. Sci. 2022, 12(12), 6073; https://0-doi-org.brum.beds.ac.uk/10.3390/app12126073 - 15 Jun 2022
Viewed by 1332
Abstract
There are quite some machine learning (ML) models, frameworks, AI-based services or products from different IT solution providers available, which can be used as building blocks to embed and use in IT solution architectures of companies. However, the path from initial prototypical proof [...] Read more.
There are quite some machine learning (ML) models, frameworks, AI-based services or products from different IT solution providers available, which can be used as building blocks to embed and use in IT solution architectures of companies. However, the path from initial prototypical proof of concept solutions until the deployment of proven systems into the operational environment remains a major challenge. The potential of AI-based software components using ML or knowledge engineering (KE) is huge and the majority of small to medium enterprises are still unsure whether their internal developer teams should be extended by additional ML or KE skills to enrich their IT solution architectures with novel AI-based components where appropriate. How can enterprises manage the change and visualize the current state and foreseeable road-map? In the current paper, we propose an AI system landscape for the public transport sector, which is based on existing AI-domains and AI-categories defined by different technical reports of the European Commission. We collect use-cases from three different enterprises in the transportation sector and visualize them on the proposed domain specific AI-landscape. We provide some insights into different maturity levels of different AI-based components and how the different ML and KE based components can be embedded into an AI-based software development life-cycle (SDLC). We visualize, how the AI-based IT-solution architecture evolved over the last decades with respect to coupling and decoupling of layers and tiers in the overall Enterprise Architecture. Full article
Show Figures

Figure 1

17 pages, 508 KiB  
Article
New Hybrid Techniques for Business Recommender Systems
by Charuta Pande, Hans Friedrich Witschel and Andreas Martin
Appl. Sci. 2022, 12(10), 4804; https://0-doi-org.brum.beds.ac.uk/10.3390/app12104804 - 10 May 2022
Cited by 4 | Viewed by 1497
Abstract
Besides the typical applications of recommender systems in B2C scenarios such as movie or shopping platforms, there is a rising interest in transforming the human-driven advice provided, e.g., in consultancy via the use of recommender systems. We explore the special characteristics of such [...] Read more.
Besides the typical applications of recommender systems in B2C scenarios such as movie or shopping platforms, there is a rising interest in transforming the human-driven advice provided, e.g., in consultancy via the use of recommender systems. We explore the special characteristics of such knowledge-based B2B services and propose a process that allows incorporating recommender systems into them. We suggest and compare several recommender techniques that allow incorporating the necessary contextual knowledge (e.g., company demographics). These techniques are evaluated in isolation on a test set of business intelligence consultancy cases. We then identify the respective strengths of the different techniques and propose a new hybridisation strategy to combine these strengths. Our results show that the hybridisation leads to substantial performance improvement over the individual methods. Full article
Show Figures

Figure 1

18 pages, 1129 KiB  
Article
Impact of Sentence Representation Matching in Neural Machine Translation
by Heeseung Jung, Kangil Kim, Jong-Hun Shin, Seung-Hoon Na, Sangkeun Jung and Sangmin Woo
Appl. Sci. 2022, 12(3), 1313; https://0-doi-org.brum.beds.ac.uk/10.3390/app12031313 - 26 Jan 2022
Cited by 1 | Viewed by 1630
Abstract
Most neural machine translation models are implemented as a conditional language model framework composed of encoder and decoder models. This framework learns complex and long-distant dependencies, but its deep structure causes inefficiency in training. Matching vector representations of source and target sentences improves [...] Read more.
Most neural machine translation models are implemented as a conditional language model framework composed of encoder and decoder models. This framework learns complex and long-distant dependencies, but its deep structure causes inefficiency in training. Matching vector representations of source and target sentences improves the inefficiency by shortening the depth from parameters to costs and generalizes NMTs with a different perspective to cross-entropy loss. In this paper, we propose matching methods to derive the cost based on constant word-embedding vectors of source and target sentences. To find the best method, we analyze the impact of the methods with varying structures, distance metrics, and model capacity in a French to English translation task. An optimally configured method is applied to English translation tasks from and to French, Spanish, and German. In the tasks, the method showed performance improvement by 3.23 BLEU at maximum, with an improvement of 0.71 on average. We evaluated the robustness of this method to various embedding distributions and models, such as conventional gated structures and transformer networks, and empirical results showed that it has a higher chance to improve performance in those models. Full article
Show Figures

Figure 1

15 pages, 668 KiB  
Article
Development of Knowledge Base Using Human Experience Semantic Network for Instructive Texts
by Hossam A. Gabbar, Sk Sami Al Jabar, Hassan A. Hassan and Jing Ren
Appl. Sci. 2021, 11(17), 8072; https://0-doi-org.brum.beds.ac.uk/10.3390/app11178072 - 31 Aug 2021
Viewed by 2271
Abstract
An organized knowledge structure or knowledge base plays a vital role in retaining knowledge where data are processed and organized so that machines can understand. Instructive text (iText) consists of a set of instructions to accomplish a task or operation. Hence, iText includes [...] Read more.
An organized knowledge structure or knowledge base plays a vital role in retaining knowledge where data are processed and organized so that machines can understand. Instructive text (iText) consists of a set of instructions to accomplish a task or operation. Hence, iText includes a group of texts having a title or name of the task or operation and step-by-step instructions on how to accomplish the task. In the case of iText, storing only entities and their relationships with other entities does not always provide a solution for capturing knowledge from iTexts as it consists of parameters and attributes of different entities and their action based on different operations or procedures and the values differ for every individual operation or procedure for the same entity. There is a research gap in iTexts that created limitations to learn about different operations, capture human experience and dynamically update knowledge for every individual operation or instruction. This research presents a knowledge base for capturing and retaining knowledge from iTexts existing in operational documents. From each iTexts, small pieces of knowledge are extracted and represented as nodes linked to one another in the form of a knowledge network called the human experience semantic network (HESN). HESN is the crucial component of our proposed knowledge base. The knowledge base also consists of domain knowledge having different classified terms and key phrases of the specific domain. Full article
Show Figures

Figure 1

17 pages, 904 KiB  
Article
KGGCN: Knowledge-Guided Graph Convolutional Networks for Distantly Supervised Relation Extraction
by Ningyi Mao, Wenti Huang and Hai Zhong
Appl. Sci. 2021, 11(16), 7734; https://0-doi-org.brum.beds.ac.uk/10.3390/app11167734 - 22 Aug 2021
Cited by 4 | Viewed by 2027
Abstract
Distantly supervised relation extraction is the most popular technique for identifying semantic relation between two entities. Most prior models only focus on the supervision information present in training sentences. In addition to training sentences, external lexical resource and knowledge graphs often contain other [...] Read more.
Distantly supervised relation extraction is the most popular technique for identifying semantic relation between two entities. Most prior models only focus on the supervision information present in training sentences. In addition to training sentences, external lexical resource and knowledge graphs often contain other relevant prior knowledge. However, relation extraction models usually ignore such readily available information. Moreover, previous works only utilize a selective attention mechanism over sentences to alleviate the impact of noise, they lack the consideration of the implicit interaction between sentences with relation facts. In this paper, (1) a knowledge-guided graph convolutional network is proposed based on the word-level attention mechanism to encode the sentences. It can capture the key words and cue phrases to generate expressive sentence-level features by attending to the relation indicators obtained from the external lexical resource. (2) A knowledge-guided sentence selector is proposed, which explores the semantic and structural information of triples from knowledge graph as sentence-level knowledge attention to distinguish the importance of each individual sentence. Experimental results on two widely used datasets, NYT-FB and GDS, show that our approach is able to efficiently use the prior knowledge from the external lexical resource and knowledge graph to enhance the performance of distantly supervised relation extraction. Full article
Show Figures

Figure 1

20 pages, 1932 KiB  
Article
Education-to-Skill Mapping Using Hierarchical Classification and Transformer Neural Network
by Vilija Kuodytė and Linas Petkevičius
Appl. Sci. 2021, 11(13), 5868; https://0-doi-org.brum.beds.ac.uk/10.3390/app11135868 - 24 Jun 2021
Cited by 2 | Viewed by 2133
Abstract
Skills gained from vocational or higher education form an essential component of country’s economy, determining the structure of the national labor force. Therefore, knowledge on how people’s education converts to jobs enables data-driven choices concerning human resources within an ever-changing job market. Moreover, [...] Read more.
Skills gained from vocational or higher education form an essential component of country’s economy, determining the structure of the national labor force. Therefore, knowledge on how people’s education converts to jobs enables data-driven choices concerning human resources within an ever-changing job market. Moreover, the relationship between education and occupation is also relevant in times of global crises, such as the COVID-19 pandemic. Healthcare system overload and skill shortage on one hand, and job losses related to lock-downs on the other, have exposed a necessity to identify target groups with relevant education backgrounds in order to facilitate their occupational transitions. However, the relationship between education and employment is complex and difficult to model. This study aims to propose the methodology that would allow us to model education-to-skill mapping. Multiple challenges arising from administrative datasets, namely imbalanced data, complex labeling, hierarchical structure and textual data, were addressed using six neural network-based algorithms of incremental complexity. The final proposed mathematical model incorporates the textual data from descriptions of education programs that are transformed into embeddings, utilizing transformer neural networks. The output of the final model is constructed as the hierarchical classification task. The effectiveness of the proposed model is demonstrated using experiments on national level data, which covers whole population of Lithuania. Finally, we provide the recommendations for the usage of proposed model. This model can be used for practical applications and scenario forecasting. Some possible applications for such model usage are demonstrated and described in this article. The code for this research has been made available on GitHub. Full article
Show Figures

Figure 1

30 pages, 779 KiB  
Article
Ontology-Based Knowledge Representation in Robotic Systems: A Survey Oriented toward Applications
by Sumaira Manzoor, Yuri Goncalves Rocha, Sung-Hyeon Joo, Sang-Hyeon Bae, Eun-Jin Kim, Kyeong-Jin Joo and Tae-Yong Kuc
Appl. Sci. 2021, 11(10), 4324; https://0-doi-org.brum.beds.ac.uk/10.3390/app11104324 - 11 May 2021
Cited by 24 | Viewed by 5730
Abstract
Knowledge representation in autonomous robots with social roles has steadily gained importance through their supportive task assistance in domestic, hospital, and industrial activities. For active assistance, these robots must process semantic knowledge to perform the task more efficiently. In this context, ontology-based knowledge [...] Read more.
Knowledge representation in autonomous robots with social roles has steadily gained importance through their supportive task assistance in domestic, hospital, and industrial activities. For active assistance, these robots must process semantic knowledge to perform the task more efficiently. In this context, ontology-based knowledge representation and reasoning (KR & R) techniques appear as a powerful tool and provide sophisticated domain knowledge for processing complex robotic tasks in a real-world environment. In this article, we surveyed ontology-based semantic representation unified into the current state of robotic knowledge base systems, with our aim being three-fold: (i) to present the recent developments in ontology-based knowledge representation systems that have led to the effective solutions of real-world robotic applications; (ii) to review the selected knowledge-based systems in seven dimensions: application, idea, development tools, architecture, ontology scope, reasoning scope, and limitations; (iii) to pin-down lessons learned from the review of existing knowledge-based systems for designing better solutions and delineating research limitations that might be addressed in future studies. This survey article concludes with a discussion of future research challenges that can serve as a guide to those who are interested in working on the ontology-based semantic knowledge representation systems for autonomous robots. Full article
Show Figures

Figure 1

Back to TopTop