Knowledge Extraction Process Research Articles

Building Digital Twins to Overcome Digitalization Barriers for Automating Construction Site Management

Construction sites are highly unpredictable environments involving a wide variety of stakeholders with complex information exchanges, which lead to the well-known inefficiencies and unproductivity of the construction sector. The adoption of Building Digital Twins (BDT) in the construction site is a promising solution to this issue, by automating data acquisition and knowledge extraction processes and providing what-if scenario simulation capabilities. Furthermore, the current research sets the principles to define, replicate, and scale-up the architecture of a Building Digital Twin Platform (BDTP), conceived as a scalar ecosystem, which allows to seamlessly manage on-site construction processes, integrating cross-cutting domains for the construction site optimization (Progress monitoring, Quality control, Operational Health and Safety, Equipment control, and Production planning). The starting point of the research is a comprehensive diagnosis of on-site process inefficiencies and the barriers to its digitalization leading to the user requirements, which have been underpinned by questionnaires and interviews addressed within an open innovation user-centered approach around Living Labs. The research has been conceived following the Design Science Research (DSR) methodology and based on the Plan-Do-Check-Act (PDCA) analysis for the continuous improvement of the construction process. By means of the adoption of the standard Business Process Model and Notation (BPMN), based on the BDTP architecture, the research has resulted in BPMN workflows stemmed from the Digital Twin (DT) where the DT itself is an actor in a service-oriented data-exchange workflow. Moreover, the use of a BDTP can pave the way for the transition from user-driven construction management to hybrid management, coexisting with both human and digital actors and merging expert knowledge with artificial intelligence techniques.

A task‐centric knowledge graph construction method based on multi‐modal representation learning for industrial maintenance automation

AbstractMaintenance manuals are crucial information sources for maintenance and repair. Prior studies explored factual knowledge extraction from textual documents. However, maintenance knowledge in manuals is more task‐centric rather than factual knowledge and often documented in an unstructured Portable Document Format (PDF), posing challenges for knowledge extraction. Addressing this, this research develops effective methods to extract task‐centric maintenance knowledge from unstructured PDF manuals. A new Task‐centric Knowledge Graph (TCKG) schema centralized on maintenance task components (MTCs) is proposed to address the need for structured knowledge representation. A method (Heterogeneous Graph‐based Method, HGM) for knowledge extraction is then proposed, which is enhanced by incorporating visual and spatial information. In the experiments, the proposed HGM exhibits robust performance in the knowledge extraction process, surpassing the baseline Graph‐based Interaction Model with a Tracker (GIT) method in MTCs extraction by 13.3%, and the baseline Translate Embedding (TransE) method in MTCs' relation extraction by 3.8%. A series of ablation studies also prove that including visual and spatial information through the proposed method can improve the relation extraction performance by over 10%. This research supplies valuable insights for future developments in information extraction from maintenance manuals.

Content Summarization and Question Answering System Using LLM

This paper presents a novel approach to content summarization, a pivotal task in information processing and knowledge extraction. Our methodology integrates cutting-edge technologies, including large language models (LLMs) and ad-vanced retrieval techniques, to efficiently distill extensive textual data into concise and informative summaries. By leveraging Anyscale LLMs for language comprehension and employing prompt engineering for model guidance, we propose a frame-work that prioritizes efficient document indexing and rapid retrieval using DuckDB vector stores. Additionally, we introduce the RetrievalQAWithSourcesChain framework, which combines LLMs with retrievers for proficient question answering. Em-pirical validation demonstrates the efficacy of our approach in generating high-quality content summaries with minimal manual intervention, thereby enhancing information retrieval and knowledge extraction processes. Index Terms—LLMs, Anyscale, prompt engineering, document indexing, DuckDB, vector stores, RetrievalQAWithSourcesChain framework, question answering, empirical validation

An Interactive Knowledge-Based Multiobjective Evolutionary Algorithm Framework for Practical Optimization Problems

Experienced users often have useful knowledge and intuition in solving real-world optimization problems. User knowledge can be formulated as inter-variable relationships to assist an optimization algorithm in finding good solutions faster. Such inter-variable interactions can also be automatically learned from high-performing solutions discovered at intermediate iterations in an optimization run – a process called innovization. These relations, if vetted by the users, can be enforced among newly generated solutions to steer the optimization algorithm towards practically promising regions in the search space. Challenges arise for large-scale problems where the number of such variable relationships may be high. This paper proposes an interactive knowledge-based evolutionary multi-objective optimization () framework that extracts hidden variable-wise relationships as knowledge from evolving high-performing solutions, shares them with users to receive feedback, and applies them back to the optimization process to improve its effectiveness. The knowledge extraction process uses a systematic and elegant graph analysis method which scales well with number of variables. The working of the proposed is demonstrated on three large-scale real-world engineering design problems. The simplicity and elegance of the proposed knowledge extraction process and achievement of high-performing solutions quickly indicate the power of the proposed framework. The results presented should motivate further such interaction-based optimization studies for their routine use in practice.

Decoupled and Explainable Associative Memory for Effective Knowledge Propagation.

Long-term memory often plays a pivotal role in human cognition through the analysis of contextual information. Machine learning researchers have attempted to emulate this process through the development of memory-augmented neural networks (MANNs) to leverage indirectly related but resourceful historical observations during learning and inference. The area of MANN, however, is still in its infancy and significant research effort is required to enable machines to achieve performance close to the human cognition process. This article presents an innovative MANN framework for the advanced incorporation of historical knowledge into a predictive framework. Within the key-value memory structure, we propose to decouple the key representations from the learned value memory embeddings to offer improved associations between the inputs and latent memory embeddings. We argue that the keys should be static, sparse, and unique representations of a particular observation to offer robust input to memory associations, while the value embeddings could be trainable, dense latent vectors such that they can better capture historical knowledge. Moreover, we introduce a novel memory update procedure that preserves the explainability of the historical knowledge extraction process, which would enable the human end-users to interpret the deep machine learning model decisions, fostering their trust. With extensive experiments conducted on three different datasets using audio, text, and image modalities, we demonstrate that our proposed innovations collectively allow this framework to outperform the current state-of-the-art methods by significant margins, irrespective of the modalities or the downstream tasks. The code is available at https://github.com/tha725/DE-KVMN/tree/main.

Enforcing legal information extraction through context-aware techniques: The ASKE approach

To cope with the growing volume, complexity, and articulation of legal documents as well as to foster digital justice and digital law, increasing effort is being devoted to legal knowledge extraction and digital transformation processes. In this paper, we present the ASKE (Automated System for Knowledge Extraction) approach to legal knowledge extraction, based on a combination of context-aware embedding models and zero-shot learning techniques into a three-phase extraction cycle, which is executed a number of times (called generations) to progressively extract concepts representative of the different meanings of terminology used in legal documents chunks. A graph-based data structure called ASKE Conceptual Graph is initially populated through a data preparation step, and it is continuously enriched at each ASKE generation with results of document chunk classification, new extracted terminology, and newly derived concepts. A quantitative evaluation of ASKE knowledge extraction and document classification is provided by considering the EurLex dataset. Furthermore, we present the results of applying ASKE to a real case-study of Italian case law decisions with qualitative feedback from legal experts in the framework of an ongoing national research project.

Unraveling COVID-19 Dynamics via Machine Learning and XAI: Investigating Variant Influence and Prognostic Classification

Machine learning (ML) has been used in different ways in the fight against COVID-19 disease. ML models have been developed, e.g., for diagnostic or prognostic purposes and using various modalities of data (e.g., textual, visual, or structured). Due to the many specific aspects of this disease and its evolution over time, there is still not enough understanding of all relevant factors influencing the course of COVID-19 in particular patients. In all aspects of our work, there was a strong involvement of a medical expert following the human-in-the-loop principle. This is a very important but usually neglected part of the ML and knowledge extraction (KE) process. Our research shows that explainable artificial intelligence (XAI) may significantly support this part of ML and KE. Our research focused on using ML for knowledge extraction in two specific scenarios. In the first scenario, we aimed to discover whether adding information about the predominant COVID-19 variant impacts the performance of the ML models. In the second scenario, we focused on prognostic classification models concerning the need for an intensive care unit for a given patient in connection with different explainability AI (XAI) methods. We have used nine ML algorithms, namely XGBoost, CatBoost, LightGBM, logistic regression, Naive Bayes, random forest, SGD, SVM-linear, and SVM-RBF. We measured the performance of the resulting models using precision, accuracy, and AUC metrics. Subsequently, we focused on knowledge extraction from the best-performing models using two different approaches as follows: (a) features extracted automatically by forward stepwise selection (FSS); (b) attributes and their interactions discovered by model explainability methods. Both were compared with the attributes selected by the medical experts in advance based on the domain expertise. Our experiments showed that adding information about the COVID-19 variant did not influence the performance of the resulting ML models. It also turned out that medical experts were much more precise in the identification of significant attributes than FSS. Explainability methods identified almost the same attributes as a medical expert and interesting interactions among them, which the expert discussed from a medical point of view. The results of our research and their consequences are discussed.

EMailMe: A Method to Build Datasets of Corporate Emails in Portuguese

One of the areas in which knowledge management has application is in companies that are concerned with maintaining and disseminating their practices among their members. However, studies involving these two domains may end up suffering from the issue of data confidentiality. Furthermore, it is difficult to find data regarding organizations processes and associated knowledge. Therefore, this paper presents a method to support the generation of a labeled dataset composed of texts that simulate corporate emails containing sensitive information regarding disclosure, written in Portuguese. The method begins with the definition of the dataset’s size and content distribution; the structure of its emails’ texts; and the guidelines for specialists to build the emails’ texts. It aims to create datasets that can be used in the validation of a tacit knowledge extraction process considering the 5W1H approach for the resulting base. The method was applied to create a dataset with content related to several domains, such as Federal Court and Registry Office and Marketing, giving it diversity and realism, while simulating real-world situations in the specialists’ professional life. The dataset generated is available in an open-access repository so that it can be downloaded and, eventually, expanded.

Bi-level algorithm for optimizing hyperparameters in penalized nonnegative matrix factorization

Learning approaches rely on hyperparameters that impact the algorithm’s performance and affect the knowledge extraction process from data. Recently, Nonnegative Matrix Factorization (NMF) has attracted a growing interest as a learning algorithm. This technique captures the latent information embedded in large datasets while preserving feature properties. NMF can be formalized as a penalized optimization task in which tuning the penalty hyperparameters is an open issue. The current literature does not provide any general framework addressing this task. This study proposes to express the penalty hyperparameters problem in NMF in terms of a bi-level optimization. We design a novel algorithm, named Alternating Bi-level (AltBi), which incorporates the hyperparameters tuning procedure into the updates of NMF factors. Results of the existence and convergence of numerical solutions, under appropriate assumptions, are studied, and numerical experiments are provided.

Fuzzy Discretization on the Multinomial Naïve Bayes Method for Modeling Multiclass Classification of Corn Plant Diseases and Pests

As an agricultural commodity, corn functions as food, animal feed, and industrial raw material. Therefore, diseases and pests pose a major challenge to the production of corn plants. Modeling the classification of corn plant diseases and pests based on digital images is essential for developing an information technology-based early detection system. This plant’s early detection technology is beneficial for lowering farmers’ losses. The detection system based on digital images is also cost-effective. This paper aims to model the classification of corn plant diseases and pests based on digital images by implementing fuzzy discretization. Discretization is an essential technique to improve the knowledge extraction process of continuous-type data. It is also essential in some methods where continuous data must be processed or handled. Fuzzy discretization allows classes to have overlapping intervals so that they can handle information that is vague or unclear. We developed hypotheses and proved that different combinations of membership functions in fuzzy discretization affect classification performance. Empirical assessment using Monte Carlo resampling was carried out to obtain the generalizability of the performance of the best classification model of all proposed models. The best model is determined based on the number of metrics with the highest value and the highest metric on the Fscore and Kappa, a multiclass measure. The combination of digital image data preprocessing and classification methods also affects the performance of the classification model. We hope this work can provide an overview for experts in building early detection systems of corn plant diseases and pests using classification models based on fuzzy discretization.

Ontology-Based Knowledge Acquisition Method for Natural Language Texts

The main task of knowledge acquisition (also named knowledge extraction) from natural language texts is to extract knowledge from natural language texts into fragment of knowledge base of intelligent system. Through the induction of the related literature about knowledge acquisition at a home country and abroad, this paper analyses the strengths and weaknesses of the classical approach. After emphatically researching the rulebased knowledge extraction technology and the method of building ontology of linguistics, this article proposes a solution to the implementation of knowledge acquisition based on the OSTIS technology. The main feature of this solution is to construct a unified semantic model that is able to utilize ontologies of linguistics (mainly, syntactic and semantic aspect) and integrate various problem-solving models (e. g., rule-based models, neural network models) for solving knowledge extraction process from natural language texts.

Examining Knowledge Extraction Processes from Heterogeneous Data Sources

In the last 20 years, e-mail, instant messaging, documents, blogs, news, text communication in the transfer of information over the web, as a result of the presentation and transmission of information as a result of the Web the dramatic increase in the amount of data in digital environments has increased the importance of studies in the field of knowledge extraction from unstructured data. Since the 2000s, one of the primary goals of researchers in the field of artificial intelligence has been to extract knowledge from heterogeneous data sources on the World Wide Web, including real-life entities and semantic relationships between entities, and to display them in machine-readable format. Advances in natural language processing and information extraction have increased the importance of large-scale knowledge bases in complex applications, resulting in scalable information extraction from semi-structured and unstructured heterogeneous data sources on the Web, and the detection of entities and relationships; It enabled the automatic creation of prominent knowledge bases in this field such as DbPedia, YAGO, NELL, Freebase, Probase, Google Knowledge Vault, IBM Watsons, which contain millions of semantic relationships between hundreds of thousands of entities, and displaying the created information in machine-readable format. Within the scope of this article; Web-scale(end-to-end) knowledge extraction from heterogeneous data sources, methods, challenges and opportunities are provided.

Problems of Automatic Processing of Scientific Texts based on Extraction of Information from Encyclopedias of Relevant Domain Areas

The article discusses the problems arising in the automatic processing of scientific texts and presents the results of work on creating a combined method for aspect-oriented analysis of scientific texts in the field of fundamental disciplines, taking into account both knowledge of the subject area and statistical methods of text processing. Thematic encyclopedias, which are not only a source of professional scientific terminology, but are considered to be an information resource for extracting knowledge about the subject area, are proposed to be used as training data. The work offers the structure of templates designed to extract information from the partially structured text of the encyclopedia, considers the structure of extracted sets of professional terms, offers the algorithm of formation of semantic relationships between special terms. The process of knowledge extraction in this paper is demonstrated on the example of processing four encyclopedias: mathematical, physical, chemical, medical. The general principles of the formation of domain scientific terminology are highlighted, and statistical data on the terminological composition in each of the examined areas is given. Within the framework of the conducted research on the basis of the texts of encyclopedias the basic semantic graphs of the corresponding scientific fields with the relations between the professional terms introduced on them are constructed. Basic graphs accumulate knowledge about the scientific field and are intended for the subsequent thematic analysis of unstructured texts of scientific articles. The Implemented algorithm of extraction of semantics of the given scientific text is based both on amplification of weights of nodes — terms of the applied domain, and on the correction of semantic relations between the nodes of the graph according to the processed text. The results of experiments on automatic construction of the list of keywords of the article are given. The results were compared with the list of keywords specified by the author of the article. It should be noted that the relevance of correctly extracted terms is mainly determined by semantic links in the basic domain graph, and depends significantly less on the number of keywords in the original article, which demonstrates the advantage of the proposed combined method compared with a simple frequency analysis. The sample analysis of the texts of the articles on mathematics showed good accuracy in the extraction of key terms compared to the list of keywords specified by the author of the article.

Artificial Intelligence and Neutrosophic Machine learning in the Diagnosis and Detection of COVID 19

The world has always suffered and from diseases and epidemics, and the coronavirus is one of the most dangerous viruses that threatened human life that requires the use of all scientific methods and means to respond to it and reduce its spread by early detection of infections and taking necessary measures In view of the significant role that artificial intelligence plays in most fields of science, it has become one of the most important scientific methods used to resolve complex issues and has been harnessed in medical diagnosis, one of the most complex areas. Many AI and machine learning algorithms have been used to diagnose and detect diseases in general and coronavirus in particular. The support vector machine (svm) machine algorithm was one of the most important algorithms in this area and is one of the most effective compilations used in the knowledge extraction process In spite of all this, the results they present remain incomplete because classification issues do not deal with cognitive uncertainties such as ambiguity, neutrality and inconsistency associated with perception of human thinking, This adversely affects the work of a classic support vector machine and affects the accurate diagnosis of the disease To solve this problem, we have done this research using a Neutrosophic Support Vector Machine because it takes into account all possible cases during the study of the sample and it reduces the impact of extreme values. This increases the accuracy of the results when diagnosing coronavirus symptoms. The study was conducted according to the following steps: 1. We extract features from chest radiographs based on GLCM 2. We form a neutrosophic dataset. 3. We train Neutrosophic Support Machine N-SVM on new data. 4. We record the results. Comparing the results, we got using the upgraded N-SVM algorithm with the classic SVM algorithm results we found that it gives a more accurate diagnosis of the disease.

Modelling digital health data: The ExaMode ontology for computational pathology

Computational pathology can significantly benefit from ontologies to standardize the employed nomenclature and help with knowledge extraction processes for high-quality annotated image datasets. The end goal is to reach a shared model for digital pathology to overcome data variability and integration problems. Indeed, data annotation in such a specific domain is still an unsolved challenge and datasets cannot be steadily reused in diverse contexts due to heterogeneity issues of the adopted labels, multilingualism, and different clinical practices. Material and methodsThis paper presents the ExaMode ontology, modeling the histopathology process by considering 3 key cancer diseases (colon, cervical, and lung tumors) and celiac disease. The ExaMode ontology has been designed bottom-up in an iterative fashion with continuous feedback and validation from pathologists and clinicians. The ontology is organized into 5 semantic areas that defines an ontological template to model any disease of interest in histopathology. ResultsThe ExaMode ontology is currently being used as a common semantic layer in: (i) an entity linking tool for the automatic annotation of medical records; (ii) a web-based collaborative annotation tool for histopathology text reports; and (iii) a software platform for building holistic solutions integrating multimodal histopathology data. DiscussionThe ontology ExaMode is a key means to store data in a graph database according to the RDF data model. The creation of an RDF dataset can help develop more accurate algorithms for image analysis, especially in the field of digital pathology. This approach allows for seamless data integration and a unified query access point, from which we can extract relevant clinical insights about the considered diseases using SPARQL queries.

Knowledge graph-based method for solutions detection and evaluation in an online problem-solving community

<span lang="EN-US">Online communities are a real medium for human experiences sharing. They contain rich knowledge of lived situations and experiences that can be used to support decision-making process and problem-solving. This work presents an approach for extracting, representing, and evaluating components of problem-solving knowledge shared in online communities. Few studies have tackled the issue of knowledge extraction and its usefulness evaluation in online communities. In this study, we propose a new approach to detect and evaluate best solutions to problems discussed by members of online communities. Our approach is based on knowledge graph technology and graphs theory enabling the representation of knowledge shared by the community and facilitating its reuse. Our process of problem-solving knowledge extraction in online communities (PSKEOC) consists of three phases: problems and solutions detection and classification, knowledge graph constitution and finally best solutions evaluation. The experimental results are compared to the World Health Organization (WHO) model chapter about Infant and young child feeding and show that our approach succeed to extract and reveal important problem-solving knowledge contained in online community’s conversations. Our proposed approach leads to the construction of an experiential knowledge graph as a representation of the constructed knowledge base in the community studied in this paper.</span>

The Nature-Based Solutions Case-Based System: A hybrid expert system

Deriving knowledge and learning from past experiences is essential for the successful adoption of Nature-Based Solutions (NBS) as novel integrative solutions that involve many uncertainties. Past experiences in implementing NBS have been collected in a number of repositories; however, it is a major challenge to derive knowledge from the huge amount of information provided by these repositories. This calls for information systems that can facilitate the knowledge extraction process. This paper introduces the NBS Case-Based System (NBS-CBS), an expert system that uses a hybrid architecture to derive information and recommendations from an NBS experience repository. The NBS-CBS combines a ‘black-box’ artificial neural networks model with a ‘white-box’ case-based reasoning model to deliver an intelligent, adaptive, and explainable system. Experts have tested this system to assess its functionality and accuracy. Accordingly, the NBS-CBS appears to provide inspirational recommendations and information for the NBS planning and design process.

Towards big industrial data mining through explainable automated machine learning

Industrial systems resources are capable of producing large amount of data. These data are often in heterogeneous formats and distributed, yet they provide means to mine the information which can allow the deployment of intelligent management tools for production activities. For this purpose, it is necessary to be able to implement knowledge extraction and prediction processes using Artificial Intelligence (AI) models, but the selection and configuration of intended AI models tend to be increasingly complex for a non-expert user. In this paper, we present an approach and a software platform that may allow industrial actors, who are usually not familiar with AI, to select and configure algorithms optimally adapted to their needs. Hence, the approach is essentially based on automated machine learning. The resulting platform effectively enables a better choice among the combination of AI algorithms and hyper-parameters configurations. It also makes it possible to provide features of explainability of the resulting algorithms and models, thus increasing the acceptability of these models in practicing community of the users. The proposed approach has been applied in the field of predictive maintenance. Current tests are based on the analysis of more than 360 databases from the subjected field.

Ontology-Based Knowledge Management Tools for Knowledge Sharing in Organization—A Review

Knowledge management (KM) comprises several processes, and one of the most important is the knowledge sharing activities. The ability of an organization to manage its organizational knowledge, specifically in the context of knowledge sharing, may enhance the organization’s overall performance. Various approaches and technologies have been introduced to assist the process in achieving that target. Ontology as one of the knowledge representation methods has been becoming popular to assist knowledge sharing in the organization. Previous reviews have mainly focused on general KM issues, with little emphasis on the use of ontology in knowledge sharing. Thus, this article reviews several ontology-based KM tools that can support knowledge-sharing activities to provide some insight into future research in this area. Thirteen ontology-based KM tools were reviewed using ten elements’ comparison criteria: the motivation, domain, source of knowledge, type of knowledge, knowledge extraction, knowledge input process, knowledge retrieval process, knowledge sharing technology, source of ontology component, and ontology methodology. The review found that several elements can be further studied to improve KM implementation in the organization, especially on the knowledge sharing dimension. This includes simplifying the knowledge extraction and retrieval process to explore various knowledge domains from implicit knowledge sources. The review’s outcome also includes proposed components and functions of an ideal ontology-based KM tool.

Research on targeted service technology for early warning information of meteorological disaster based on NLP

Affected by global climate change and the superposition of urban construction, the climate of city meteorological guarantee service puts forward new requirements and new challenges. As the first line of defense of meteorological disaster prevention and reduction, it is very important to realize the refinement targeted service of early warning information. There are some problems in the traditional early warning information service, such as the difficulty of accurate service of early warning information, the lack of precision, and the insufficient mining of early warning text information. This paper mainly analyzes the text description characteristics of early warning information of meteorological disaster, constructs the early warning information knowledge extraction process, constructs the early warning information labeling system, and realizes the early warning effective time extraction method based on conditional random field model, Early warning affected areas extraction method based on bidirectional long-term and short-term memory neural network and early warning cautions extraction method based on bootstrapping weak supervised learning method. Finally, taking the early warning information targeting service of meteorological information decision support system as an example, this paper tests the early warning information extraction methods, and preliminarily realizes the early warning precision targeting service in the decision support service of meteorological disaster prevention and reduction.