Domain-specific Knowledge Graph Research Articles

Construction and application of an ontology-based domain-specific knowledge graph for petroleum exploration and development

The massive amount and multi-sourced, multi-structured data in the upstream petroleum industry impose great challenge on data integration and smart application. Knowledge graph, as an emerging technology, can potentially provide a way to tackle the challenges associated with oil and gas big data. This paper proposes an engineering-based method that can improve upon traditional natural language processing to construct the domain knowledge graph based on a petroleum exploration and development ontology. The exploration and development knowledge graph is constructed by assembling Sinopec’s multi-sourced heterogeneous database, and millions of nodes. The two applications based on the constructed knowledge graph are developed and validated for effectiveness and advantages in providing better knowledge services for the oil and gas industry.

A visual reasoning-based approach for mutual-cognitive human-robot collaboration

Human-robot collaboration (HRC) allows seamless communication and collaboration between humans and robots to fulfil flexible manufacturing tasks in a shared workspace. Nevertheless, existing HRC systems lack an efficient integration of robotic and human cognitions. Empowered by advanced cognitive computing, this paper proposes a visual reasoning-based approach for mutual-cognitive HRC. Firstly, a domain-specific HRC knowledge graph is established. Next, the holistic manufacturing scene is perceived by visual sensors as a temporal graph. Then, a collaborative mode with similar instructions can be inferred by graph embedding. Lastly, mutual-cognitive decisions are immersed into the Augmented Reality execution loop for intuitive HRC support.

Automated Question-Answering for Interactive Decision Support in Operations & Maintenance of Wind Turbines

Intelligent question-answering (QA) systems have witnessed increased interest in recent years, particularly in their ability to facilitate information access, data interpretation or decision support. The wind energy sector is one of the most promising sources of renewable energy, yet turbines regularly suffer from failures and operational inconsistencies, leading to downtimes and significant maintenance costs. Addressing these issues requires rapid interpretation of complex and dynamic data patterns under time-critical conditions. In this article, we present a novel approach that leverages interactive, natural language-based decision support for operations & maintenance (O&M) of wind turbines. The proposed interactive QA system allows engineers to pose domain-specific questions in natural language, and provides answers (in natural language) based on the automated retrieval of information on turbine sub-components, their properties and interactions, from a bespoke domain-specific knowledge graph. As data for specific faults is often sparse, we propose the use of paraphrase generation as a way to augment the existing dataset. Our QA system leverages encoder-decoder models to generate Cypher queries to obtain domain-specific facts from the KG database in response to user-posed natural language questions. Experiments with an attention-based sequence-to-sequence (Seq2Seq) model and a transformer show that the transformer accurately predicts up to 89.75% of responses to input questions, outperforming the Seq2Seq model marginally by 0.76%, though being 9.46 times more computationally efficient. The proposed QA system can help support engineers and technicians during O&M to reduce turbine downtime and operational costs, thus improving the reliability of wind energy as a source of renewable energy.

Research on knowledge graph alignment model based on deep learning

The construction of large-scale knowledge graphs from heterogeneous sources is fundamental to knowledge-driven applications. To solve the problem of redundancy and inconsistency in the process of domain knowledge fusion, this paper reports studies of domain knowledge alignment from the perspective of a knowledge graph. A novel knowledge graph alignment (KGA) model is proposed, based on knowledge graph deep representation learning. To assess the validity of the model, comparative experiments are conducted on the datasets of heterogeneous, cross-lingual, and domain-specific knowledge graphs. Our results of experiments suggest significant improvement on all of these datasets. We discuss the implications for improving the alignment effect of knowledge graph entities, enhancing the coverage and correctness of knowledge graphs, and promoting the performance of knowledge graphs in knowledge-driven applications.

Using Knowledge Graphs to Plausibly Infer Missing Associations in EMR Data.

Electronic Medical Records (EMRs) are increasingly being deployed at primary points of care and clinics for digital record keeping, increasing productivity and improving communication. In practice, however, there still exists an often incomplete picture of patient profiles, not only because of disconnected EMR systems but also due to incomplete EMR data entry - often caused by clinician time constraints and lack of data entry restrictions. To complete a patient's partial EMR data, we plausibly infer missing causal associations between medical EMR concepts, such as diagnoses and treatments, for situations that lack sufficient raw data to enable machine learning methods. We follow a knowledge-based approach, where we leverage open medical knowledge sources such as SNOMED-CT and ICD, combined with knowledge-based reasoning with explainable inferences, to infer clinical encounter information from incomplete medical records. To bootstrap this process, we apply a semantic Extract-Transform-Load process to convert an EMR database into an enriched domain-specific Knowledge Graph.

Relational Learning Analysis of Social Politics using Knowledge Graph Embedding

Knowledge Graphs (KGs) have gained considerable attention recently from both academia and industry. In fact, incorporating graph technology and the copious of various graph datasets have led the research community to build sophisticated graph analytics tools, which has extended the application of KGs to tackle a plethora of real-life problems in dissimilar domains. Despite the abundance of the currently proliferated generic KGs, there is a vital need to construct domain-specific KGs. Further, quality and credibility should be assimilated in the process of constructing and augmenting KGs, particularly those propagated from mixed-quality resources such as social media data. For example, the amount of the political discourses in social media is overwhelming yet can be hijacked and misused by spammers to spread misinformation and false news. This paper presents a novel credibility domain-based KG Embedding framework. This framework involves capturing a fusion of data related to politics domain and obtained from heterogeneous resources into a formal KG representation depicted by a politics domain ontology. The proposed approach makes use of various knowledge-based repositories to enrich the semantics of the textual contents, thereby facilitating the interoperability of information. The proposed framework also embodies a domain-based social credibility module to ensure data quality and trustworthiness. The utility of the proposed framework is verified by means of experiments conducted on two constructed KGs. The KGs are then embedded in low-dimensional semantically-continuous space using several embedding techniques. The effectiveness of embedding techniques and social credibility module is further demonstrated and substantiated on link prediction, clustering, and visualisation tasks.

Research on Entity Label Value Assignment Method in Knowledge Graph

The lack of entity label values is one of the problems faced by the application of Knowledge Graph. The method of automatically assigning entity label values still has shortcomings, such as costing more resources during training, leading to inaccurate label value assignment because of lacking entity semantics. In this paper, oriented to domain-specific Knowledge Graph, based on the situation that the initial entity label values of all triples are completely unknown, an Entity Label Value Assignment Method (ELVAM) based on external resources and entropy is proposed. ELVAM first constructs a Relationship Triples Cluster according to the relationship type, and randomly extracts the triples data from each cluster to form a Relationship Triples Subset; then collects the extended semantic text of the entities in the subset from the external resources to obtain nouns. Information Entropy and Conditional Entropy of the nouns are calculated through Ontology Category Hierarchy Graph, so as to obtain the entity label value with moderate granularity. Finally, the Label Triples Pattern of each Relationship Triples Cluster is summarized, and the corresponding entity is assigned the label value according to the pattern. The experimental results verify the effectiveness of ELVAM in assigning entity label values in Knowledge Graph.

Knowledge archaeology on relations between the Venice Architecture Biennale (1980–2018) and the Pritzker Architecture Prize (1979–2019)

ABSTRACT This paper used a philosophy method called knowledge archaeology to identify the relations between the Venice Architecture Biennale and the Pritzker Architecture Prize. Two questions were posed: (1) “Who is speaking” in the biennale and prize, respectively? (2) Do the biennale and curating change architectural thinking? Through knowledge archaeology, the domain-specific knowledge graphs of the Venice Architecture Biennale participants and the Pritzker Architecture Prize laureates are compared from three aspects: “persons,” “words,” and “Asia.” Comparing the number, type, and nationality of exhibitors and laureates, the importance of the biennale and its influence on architectural development are confirmed. Results show that the thinking and curating of the Venice Architecture Biennale have influenced and changed who wins the Pritzker Architecture Prize. Moreover, Asian architects played increasingly important roles in the exhibition and prize process. Starting from the architectural exhibition, we can connect the entire architectural world. In other words, we may be able to “curate the whole world.”

Deep Learning-Based Knowledge Graph Generation for COVID-19

Many attempts have been made to construct new domain-specific knowledge graphs using the existing knowledge base of various domains. However, traditional “dictionary-based” or “supervised” knowledge graph building methods rely on predefined human-annotated resources of entities and their relationships. The cost of creating human-annotated resources is high in terms of both time and effort. This means that relying on human-annotated resources will not allow rapid adaptability in describing new knowledge when domain-specific information is added or updated very frequently, such as with the recent coronavirus disease-19 (COVID-19) pandemic situation. Therefore, in this study, we propose an Open Information Extraction (OpenIE) system based on unsupervised learning without a pre-built dataset. The proposed method obtains knowledge from a vast amount of text documents about COVID-19 rather than a general knowledge base and add this to the existing knowledge graph. First, we constructed a COVID-19 entity dictionary, and then we scraped a large text dataset related to COVID-19. Next, we constructed a COVID-19 perspective language model by fine-tuning the bidirectional encoder representations from transformer (BERT) pre-trained language model. Finally, we defined a new COVID-19-specific knowledge base by extracting connecting words between COVID-19 entities using the BERT self-attention weight from COVID-19 sentences. Experimental results demonstrated that the proposed Co-BERT model outperforms the original BERT in terms of mask prediction accuracy and metric for evaluation of translation with explicit ordering (METEOR) score.

Construction and Application Technology Architecture of Domain-specific Knowledge Graphin Military Field

Domain-specific Knowledge Graph in Military Field is a bridge to connect all kinds of battle factors, such as combat forces, command system, weapon platforms. It’s also an important means to break through the information gap between different areas of different services. Most of the existing knowledge graph is general knowledge graph for general fields, but there is no mature method of knowledge graph construction and expression for the industry data of military specific fields. So based on the special needs for military knowledge acquisition, storage, representation, query and other technologies in the future information and intelligent operations, and application scenarios, this paper discusses the current opportunities and challenges of the knowledge graph in military domain. Then the construction of knowledge graph in military domain and application technology framework are proposed.

Pattern-based design applied to cultural heritage knowledge graphs

Ontology Design Patterns (ODPs) have become an established and recognised practice for guaranteeing good quality ontology engineering. There are several ODP repositories where ODPs are shared as well as ontology design methodologies recommending their reuse. Performing rigorous testing is recommended as well for supporting ontology maintenance and validating the resulting resource against its motivating requirements. Nevertheless, it is less than straightforward to find guidelines on how to apply such methodologies for developing domain-specific knowledge graphs. ArCo is the knowledge graph of Italian Cultural Heritage and has been developed by using eXtreme Design (XD), an ODP- and test-driven methodology. During its development, XD has been adapted to the need of the CH domain e.g. gathering requirements from an open, diverse community of consumers, a new ODP has been defined and many have been specialised to address specific CH requirements. This paper presents ArCo and describes how to apply XD to the development and validation of a CH knowledge graph, also detailing the (intellectual) process implemented for matching the encountered modelling problems to ODPs. Relevant contributions also include a novel web tool for supporting unit-testing of knowledge graphs, a rigorous evaluation of ArCo, and a discussion of methodological lessons learned during ArCo’s development.

The Named Entity Recognition of Chinese Cybersecurity Using an Active Learning Strategy

In data‐driven big data security analysis, knowledge graph‐based multisource heterogeneous threat data organization, association mining, and inference analysis attach increasinginterest in the field of cybersecurity. Although the construction of knowledge graph based on deep learning has achieved great success, the construction of a largescale, high‐quality, and domain‐specific knowledge graph needs a manual annotation of large corpora, which means it is very difficult. To tackle this problem, we present a straightforward active learning strategy for cybersecurity entity recognition utilizing deep learning technology. BERT pre‐trained model and residual dilation convolutional neural networks (RDCNN) are introduced to learn entity context features, and the conditional random field (CRF) layer is employed as a tag decoder. Then, taking advantages of the output results and distribution of cybersecurity entities, we propose an active learning strategy named TPCL that considers the uncertainty, confidence, and diversity. We evaluated TPCL on the general domain datasets and cybersecurity datasets, respectively. The experimental results show that TPCL performs better than the traditional strategies in terms of accuracy and F1. Moreover, compared with the general field, it has better performance in the cybersecurity field and is more suitable for the Chinese entity recognition task in this field.

Research on Knowledge Driven Intelligent Question Answering System for Electric Power Customer Service

The electric power customer service domain-specific knowledge graph aims to describe the concepts, entities, events and their relationships in the electric power customer service business field, with a structured manner, and provide a more effective data organization, management, and cognitive ability for the customer service business. This paper proposes a method for constructing a knowledge graph in the field of electric customer service, and constructs a knowledge graph with over 15,000 entities and 20,000 relationships. Based on the knowledge graph, an intelligent question answering application architecture is designed, which consists of multiple functional modules such as dialogue process configuration, natural language processing, and business process processing. It provides more efficient and open knowledge retrieval services for the electric customer service business, and improves the intelligence level of customer service question answering.

Predictive article recommendation using natural language processing and machine learning to support evidence updates in domain-specific knowledge graphs

ObjectivesDescribe an augmented intelligence approach to facilitate the update of evidence for associations in knowledge graphs.MethodsNew publications are filtered through multiple machine learning study classifiers, and filtered publications are combined with articles already included as evidence in the knowledge graph. The corpus is then subjected to named entity recognition, semantic dictionary mapping, term vector space modeling, pairwise similarity, and focal entity match to identify highly related publications. Subject matter experts review recommended articles to assess inclusion in the knowledge graph; discrepancies are resolved by consensus.ResultsStudy classifiers achieved F-scores from 0.88 to 0.94, and similarity thresholds for each study type were determined by experimentation. Our approach reduces human literature review load by 99%, and over the past 12 months, 41% of recommendations were accepted to update the knowledge graph.ConclusionIntegrated search and recommendation exploiting current evidence in a knowledge graph is useful for reducing human cognition load.

Figure 3-6 of a paper "KnowPoetry_A Knowledge Service Platform for Tang Poetry Research based on Domain-Specific Knowledge Graph"

Figure 3-6 of a paper "KnowPoetry_A Knowledge Service Platform for Tang Poetry Research based on Domain-Specific Knowledge Graph"

KnowPoetry: A Knowledge Service Platform for Tang Poetry Research Based on Domain-Specific Knowledge Graph

KnowPoetry: A Knowledge Service Platform for Tang Poetry Research Based on Domain-Specific Knowledge Graph

Automated domain-specific healthcare knowledge graph curation framework: Subarachnoid hemorrhage as phenotype

To derive meaningful insights from voluminous healthcare data, it is essential to convert it into machine understandable knowledge. Currently, machine understandable domain specific healthcare knowledge curation framework does not exist for complex neurological diseases such as subarachnoid hemorrhage stroke. We envisage futuristic clinical decision support systems and tools backed with such knowledge will aide in complex neurological disease prognosis, diagnosis, and treatment. Existing knowledge graphs (KGs) only contain concepts and relationships between them and offer this knowledge to information extraction and knowledge management applications. However, the proposed domain-specific automated KG curation framework enables extraction of concepts, relationships, individual and cohort graphs, and predictive knowledge. By employing ontology-based information extraction, ensemble learning and word embedding based on skip-gram techniques on structured and unstructured data from electronic health records of 1025 patients with an intracranial aneurysm, this paper proposes a novel fully automated framework to curate knowledge graph, consisting of concepts, different hierarchical and non-hierarchical relationships, and predictive rules for prediction of subarachnoid hemorrhage. The evaluation shows that proposed framework achieves 78% precision and 71% recall respectively, for concept extraction from clinical text. Taxonomic relationships evaluation had precision and recall of 68%, and 95%, respectively. Evaluation of knowledge to predict unruptured status using validation dataset shows accuracy, precision, recall, of 73%, 76%, and 90% respectively.

Constructing biomedical domain-specific knowledge graph with minimum supervision

Domain-specific knowledge graph is an effective way to represent complex domain knowledge in a structured format and has shown great success in real-world applications. Most existing work on knowledge graph construction and completion shares several limitations in that sufficient external resources such as large-scale knowledge graphs and concept ontologies are required as the starting point. However, such extensive domain-specific labeling is highly time-consuming and requires special expertise, especially in biomedical domains. Therefore, knowledge extraction from unstructured contexts with minimum supervision is crucial in biomedical fields. In this paper, we propose a versatile approach for knowledge graph construction with minimum supervision based on unstructured biomedical domain-specific contexts including the steps of entity recognition, unsupervised entity and relation embedding, latent relation generation via clustering, relation refinement and relation assignment to assign cluster-level labels. The experimental results based on 24,687 unstructured biomedical science abstracts show that the proposed framework can effectively extract 16,192 structured facts with high precision. Moreover, we demonstrate that the constructed knowledge graph is a sufficient resource for the task of knowledge graph completion and new knowledge inference from unseen contexts.

KGDDS: A System for Drug-Drug Similarity Measure in Therapeutic Substitution based on Knowledge Graph Curation.

Measuring drug-drug similarity is important but challenging. Significant progresses have been made in drugs whose labeled training data is sufficient and available. However, handling data skewness and incompleteness with domain-specific knowledge graph, is still a relatively new territory and an under-explored prospect. In this paper, we present a system KGDDS for node-link-based bio-medical Knowledge Graph curation and visualization, aiding Drug-Drug Similarity measure. Specifically, we reuse existing knowledge bases to alleviate the difficulties in building a high-quality knowledge graph, ranging in size up to 7 million edges. Then we design a prediction model to explore the pharmacology features and knowledge graph features. Finally, we propose a user interaction model to allow the user to better understand the drug properties from a drug similarity perspective and gain insights that are not easily observable in individual drugs. Visual result demonstration and experimental results indicate that KGDDS can bridge the user/caregiver gap by facilitating antibiotics prescription knowledge, and has remarkable applicability, outperforming existing state-of-the-art drug similarity measures.

From Vision to Content: Construction of Domain-Specific Multi-Modal Knowledge Graph

Knowledge graphs are usually constructed to describe the various concepts that exist in real world as well as the relationships between them. There are many knowledge graphs in specific fields, but they usually pay more attention on text or structured data, ignoring the image vision information, and cannot play an adequate role in the emerging visualization applications. Aiming at this issue, we design a method that integrates image vision information and text information derived from Wikimedia Commons to construct a domain-specific multi-modal knowledge graph, taking the metallic materials domain as an example to illustrate the method. The text description of each image is regarded as its context semantic to acquire the image's context semantic labels based on the DBpedia resource. Furthermore, we adopt deep neural network model instead of simple visual descriptors to acquire the image's visual semantic labels using the concepts from WordNet. In order to fuse the visual semantic labels and context semantic labels, a path-based concept extension and fusion strategy is proposed based on the conceptual hierarchies of WordNet and DBpedia to obtain the effective extension concepts as well as the links between them, increasing the scale of the knowledge graph and enhancing the correlation between images. The experimental results show that the maximum extension level has a significant impact on the quality of the generated domain knowledge graph, and the best extension level number is respectively determined for both DBpedia and WordNet. In addition, the results of this paper are compared with IMGpedia to further show the effectiveness of the proposed method.