Entity Information Research Articles

Fine-grained partial discharge pattern recognition method based on substation equipment knowledge graph

Discharge-type faults are one of the main types of faults in substation equipment, and partial discharge (PD) faults are an important cause of equipment discharge faults. When different types of PD faults occur in equipment, their fault handling plans also vary accordingly. Therefore, the identification of PD types in equipment is very important. Aiming at the problem that the recognition accuracy of the existing methods is not high enough due to the low quality of PD data and unbalanced samples in the process of equipment PD pattern recognition, we propose a fine-grained method to recognize PD patterns based on substation equipment knowledge graph. This model combines a visual encoder with a knowledge graph and uses the fine-grained attribute features and the association feature information of the PD entity provided by the knowledge graph for the research of equipment PD pattern recognition. After experimental verification, the accuracy of PD pattern recognition in our proposed method is significantly higher than that of previous methods.

GLSEC: Global and local semantic-enhanced contrastive framework for knowledge graph completion

Knowledge graph completion (KGC) aims to infer missing links between entities in knowledge graphs (KGs). Recently, models based on graph neural networks (GNNs) have gained widespread attention due to their effectiveness in leveraging the topological structure information of entities. Meanwhile, contrastive learning (CL) has been employed in GNNs-based models to provide more supervised signals for better entity representation in a self-supervised manner. However, existing methods overlook the potential global semantic collaboration among entities within the entire KG. And the application of CL in KGC models often adopt random graph augmentation or basic node structure contrast, leading to suboptimal performance. To tackle them, we propose a Global and Local Semantic-Enhanced Contrastive Framework (GLSEC) for KGC. Specifically, we develop a global Attribute-aware encoder to capture the global semantic features of entities based on an entity-entity Attribute Interaction Graph (AIG). Additionally, we design a Light Graph Aggregation Network (Light-GAN) that innovatively updates the global semantic features using the AIG, combining both efficiency and a lightweight design. Furthermore, we introduce a Global-Local cross-view Contrastive Learning (GLCL) method that contrasts embeddings from global and local views, thereby improving contrastive sample quality and boosting the model’s understanding of entities in various contexts. Extensive experiments show that our model outperforms state-of-the-art KGC methods on benchmark datasets FB15k-237 and WN18RR.

Joint Information Extraction Model Based on Feature Sharing

To address the challenge of efficiently and accurately extracting entities, relationships, and events from unstructured text, a joint information extraction model based on feature sharing is proposed. This model utilizes the contextual information of entities, relationships, and events, and integrates entity extraction, relationship extraction, and event extraction tasks through a multi-feature cascade encoder to achieve joint extraction. To validate the effectiveness of the model, comparative analysis was conducted on military news datasets, comparing against two typical information extraction models. Results demonstrated superiority over current state-of-the-art baselines.

Question Calibration and Multi-Hop Modeling for Temporal Question Answering

Many models that leverage knowledge graphs (KGs) have recently demonstrated remarkable success in question answering (QA) tasks. In the real world, many facts contained in KGs are time-constrained thus temporal KGQA has received increasing attention. Despite the fruitful efforts of previous models in temporal KGQA, they still have several limitations. (I) They adopt pre-trained language models (PLMs) to obtain question representations, while PLMs tend to focus on entity information and ignore entity transfer caused by temporal constraints, and finally fail to learn specific temporal representations of entities. (II) They neither emphasize the graph structure between entities nor explicitly model the multi-hop relationship in the graph, which will make it difficult to solve complex multi-hop question answering. To alleviate this problem, we propose a novel Question Calibration and Multi-Hop Modeling (QC-MHM) network. Specifically, We first calibrate the question representation by fusing the question and the time-constrained concepts in KG. Then, we construct the GNN layer to complete multi-hop message passing. Finally, the question representation is combined with the embedding output by the GNN to generate the final prediction. Empirical results verify that the proposed model achieves better performance than the state-of-the-art models in the benchmark dataset. Notably, the Hits@1 and Hits@10 results of QC-MHM on the CronQuestions dataset's complex questions are absolutely improved by 5.1% and 1.2% compared to the best-performing baseline. Moreover, QC-MHM can generate interpretable and trustworthy predictions.

Mixed Geometry Message and Trainable Convolutional Attention Network for Knowledge Graph Completion

Knowledge graph completion (KGC) aims to study the embedding representation to solve the incompleteness of knowledge graphs (KGs). Recently, graph convolutional networks (GCNs) and graph attention networks (GATs) have been widely used in KGC tasks by capturing neighbor information of entities. However, Both GCNs and GATs based KGC models have their limitations, and the best method is to analyze the neighbors of each entity (pre-validating), while this process is prohibitively expensive. Furthermore, the representation quality of the embeddings can affect the aggregation of neighbor information (message passing). To address the above limitations, we propose a novel knowledge graph completion model with mixed geometry message and trainable convolutional attention network named MGTCA. Concretely, the mixed geometry message function generates rich neighbor message by integrating spatially information in the hyperbolic space, hypersphere space and Euclidean space jointly. To complete the autonomous switching of graph neural networks (GNNs) and eliminate the necessity of pre-validating the local structure of KGs, a trainable convolutional attention network is proposed by comprising three types of GNNs in one trainable formulation. Furthermore, a mixed geometry scoring function is proposed, which calculates scores of triples by novel prediction function and similarity function based on different geometric spaces. Extensive experiments on three standard datasets confirm the effectiveness of our innovations, and the performance of MGTCA is significantly improved compared to the state-of-the-art approaches.

Improving the Robustness of Knowledge-Grounded Dialogue via Contrastive Learning

Knowledge-grounded dialogue (KGD) learns to generate an informative response based on a given dialogue context and external knowledge (e.g., knowledge graphs; KGs). Recently, the emergence of large language models (LLMs) and pre-training techniques has brought great success to knowledge-grounded dialogue. However, when building KGD systems in real applications, there are various real-world noises that are inevitable to face. For example, the dialogue context might involve perturbations such as misspellings and abbreviations. In addition, KGs typically suffer from incompletion and also might contain erroneous and outdated facts. Such real-world noises pose a challenge to the robustness of KGD systems and hinder their applications in the real world. In this paper, we propose an entity-based contrastive learning framework for improving the robustness of KGD. Specifically, we make use of the entity information in a KGD sample to create both its positive and negative samples which involve semantic-irrelevant and semantic-relevant perturbations, respectively. The contrastive learning framework ensures the KGD model is aware of these two types of perturbations, thus could generate informative responses with the potentially noisy inputs in real applications. Experimental results on three widely-used benchmark datasets show that our method achieves new state-of-the-art performance in terms of automatic evaluation scores, verifying its effectiveness and potentiality. Furthermore, we show that our method is able to generate better responses than comparison models in both the noisy and the few-shot settings.

Disclosure of information on ultimate beneficial owners: from theory to practice

Ukraine has taken a significant step in the direction of transparency and fighting corruption, becoming one of the first countries in the world to disclose information about the beneficial owners of companies and make it publicly available. On 14 October 2014, the relevant Law of Ukraine "On Prevention and Fighting the Legalisation (Laundering) of Criminal Proceeds, Financing of Terrorism and Financing of the Proliferation of Weapons of Mass Destruction” was adopted, according to which all legal entities are required to submit to the Unified State Register of Legal Entities, individuals-entrepreneurs and public formations (hereinafter referred to as EDR) information about their ultimate beneficial owners.
 This historic initiative was an unequivocal breakthrough for Ukraine in ensuring transparency and openness in the field of disclosure of ownership of legal entities. This Law brought Ukraine's anti­money laundering and terrorist financing system up to international standards (the implementation of EU Directive 2015/849). The availability of information on beneficial owners has not only increased trust in government regulation, but has also made the country an example for other countries seeking to fight corruption and ensure a fair and transparent business environment.
 The law improved the system of financial monitoring, in particular regarding the application of a risk-oriented approach by subjects of primary financial monitoring. International organizations and the world community understand the importance of disclosure of information about the beneficial owners of companies, therefore it is reflected in a number of international legal acts. Ukraine is actively implementing international standards into national legislation, which confirms the high level of Ukraine's obligations to the international community in the fight against corruption and financial crimes.

Document-Level Relation Extraction with Deep Gated Graph Reasoning

Extracting the relations of two entities on the sentence-level has drawn increasing attention in recent years but remains facing great challenges on document-level, due to the inherent difficulty in recognizing the relations of two entities across multiple sentences. Previous works show that employing the graph convolutional neural network can help the model capture unstructured dependent information of entities. However, they usually employed the non-adaptive weight edges to build the correlation weight matrix which suffered from the problem of information redundancy and gradient disappearance. To solve this problem, we propose a deep gated graph reasoning model for document-level relation extraction, namely, BERT-GGNNs, which employ an improved gated graph neural network with a learnable correlation weight matrix to establish multiple deep gated graph reason layers. The proposed deep gated graph reasoning layers make the model easier to reasoning the relations between entities hidden in the document. Experiments show that the proposed model outperforms most of strong baseline models, and our proposed model is 0.3% and 0.3% higher than the famous LSR-BERT model on the F1 and Ing F1, respectively.

NPEL: Neural Paired Entity Linking in Web Tables

This paper studies entity linking (EL) in Web tables, which aims to link the string mentions in table cells to their referent entities in a knowledge base. Two main problems exist in previous studies: 1) contextual information is not well utilized in mention-entity similarity computation; 2) the assumption on entity coherence that all entities in the same row or column are highly related to each other is not always correct. In this paper, we propose NPEL , a new N eural P aired E ntity L inking framework, to overcome the above problems. In NPEL, we design a deep learning model with different neural networks and an attention mechanism, to model different kinds of contextual information of mentions and entities, for mention-entity similarity computation in Web tables. NPEL also relaxes the above assumption on entity coherence by a new paired entity linking algorithm, which iteratively selects two mentions with the highest confidence for EL. Experiments on real-world datasets exhibit that NPEL has the best performance compared with state-of-the-art baselines in different evaluation metrics.

A novel joint extraction model based on cross-attention mechanism and global pointer using context shield window

Relational triple extraction is a critical step in knowledge graph construction. Compared to pipeline-based extraction, joint extraction is gaining more attention because it can better utilize entity and relation information without causing error propagation issues. Yet, the challenge with joint extraction lies in handling overlapping triples. Existing approaches adopt sequential steps or multiple modules, which often accumulate errors and interfere with redundant data. In this study, we propose an innovative joint extraction model with cross-attention mechanism and global pointers with context shield window. Specifically, our methodology begins by inputting text data into a pre-trained RoBERTa model to generate word vector representations. Subsequently, these embeddings are passed through a modified cross-attention layer along with entity type embeddings to address missing entity type information. Next, we employ the global pointer to transform the extraction problem into a quintuple extraction problem, which skillfully solves the issue of overlapping triples. It is worth mentioning that we design a context shield window on the global pointer, which facilitates the identification of correct entities within a limited range during the entity extraction process. Finally, the capability of our model against malicious samples is improved by adding adversarial training during the training process. Demonstrating superiority over mainstream models, our approach achieves impressive results on three publicly available datasets.

Higher-order GNN with Local Inflation for entity alignment

In the age of massive data, the construction of knowledge graph has increasingly become a forceful support for the downstream applications of artificial intelligence. However, the information of entities in knowledge graphs is usually incomplete, so it is urgent to supplement the relations of entities through entity alignment task. Frustratingly, the current entity alignment models are facing serious challenges. First, some models only focus on structural features and other auxiliary information (e.g., attributes, images and descriptions), but ignore the features of the entity itself can be scaled resulting in over-smoothing issue. Second, most models utilize higher-order networks to aggregate neighborhood information by stacking layers, but the training cost of these models are drastically higher. Third, most models are supervised or semi-supervised, but there are few pre-aligned seeds for alignment, which greatly limits the improvement of model performance. Hence, to address the above three issues, we propose a Higher-Order Graph Neural Network with Local Inflation for entity alignment, named HOLI-GNN. Specifically, we introduce a local inflation mechanism, which enlarges the each feature of entities to mitigate the impact of over-smoothing caused by neighborhood aggregation. Additionally, we propose a novel higher-order encoder to capture higher-order information. Furthermore, our model also employ currently popular iteration strategy to increase labeled entity pairs, which can markedly promote the performance of align task. Finally, we perform comprehensive experiments to validate the effectiveness of our model on benchmark datasets. The results strongly indicate that our model exhibits better performance than the state-of-the-art models.

Lorentz equivariant model for knowledge-enhanced hyperbolic collaborative filtering

Introducing prior auxiliary information from the knowledge graph (KG) to assist the user–item graph can improve the comprehensive performance of the recommender system. Many recent studies have shown that the ensemble properties of hyperbolic spaces fit the scale-free and hierarchical characteristics exhibited in the above two types of graphs well. Therefore, hyperbolic-based recommender systems have achieved a series of outstanding performances. However, in existing hyperbolic methods, equivariance is not considered. Thus, they cannot generalize symmetric features under given transformations, which seriously limits the capability of the model. Moreover, they cannot balance preserving the heterogeneity and mining the high-order entity information to users across two graphs. To fill these gaps, we propose a rigorous Lorentz group equivariant knowledge-enhanced collaborative filtering (LECF) model. Innovatively, we jointly update the attribute embeddings (containing the high-order entity signals from the KG) and hyperbolic embeddings (the distance between hyperbolic embeddings reveals the recommendation tendency) via the LECF layer with Lorentz Equivariant Transformation. Moreover, we propose Hyperbolic Sparse Attention Mechanism to sample the most informative neighboring nodes. Lorentz equivariance is strictly maintained throughout the entire model, and enforcing equivariance is proven necessary experimentally. Extensive experiments on three real-world datasets demonstrate that the proposed LECF remarkably outperforms state-of-the-art methods.

CRmod: Context-Aware Rule-Guided reasoning over temporal knowledge graph

Temporal knowledge graphs have been widely used in artificial intelligence, but they are still incomplete. Therefore, the reasoning task is still a research hotspot. The existing temporal knowledge graph reasoning methods are mainly based on embedding. These methods do not take the textual information of entities and relations into account, making the reasoning results not relevant. Besides, other reasoning methods ignore interpretable logic rules. To improve reasoning results relevance and interpretability, we propose the temporal knowledge graph reasoning model CRmod (Context-aware Rule-guided model). Through the confidence of contextual neighbors and the relevance of different neighbor 4-tuples, CRmod takes context information into account and improves the relevance of reasoning results. At the same time, considering the diversity of path rules, six temporal logic rules are proposed. Besides, time information consistency of temporal logic rules is constrained, which achieves the effect of real-time reasoning. We evaluated our model on three datasets: ICEWS18, ICEWS05-15, and GDELT. Specifically, in the experimental results concerning the Mean Reciprocal Rank (MRR) metric on the ICEWS18 and ICEWS05-15 datasets, our model showed improvements over the previous State-Of-The-Art (SOTA) models by 3.24% and 16.88%, respectively. Experiments show that CRmod does improve the relevance and interpretability of the reasoning results compared with the existing temporal knowledge graph reasoning models.

On the challenges of global entity-aware deep learning models for groundwater level prediction

Abstract. The application of machine learning (ML) including deep learning models in hydrogeology to model and predict groundwater level in monitoring wells has gained some traction in recent years. Currently, the dominant model class is the so-called single-well model, where one model is trained for each well separately. However, recent developments in neighbouring disciplines including hydrology (rainfall–runoff modelling) have shown that global models, being able to incorporate data of several wells, may have advantages. These models are often called “entity-aware models“, as they usually rely on static data to differentiate the entities, i.e. groundwater wells in hydrogeology or catchments in surface hydrology. We test two kinds of static information to characterize the groundwater wells in a global, entity-aware deep learning model set-up: first, environmental features that are continuously available and thus theoretically enable spatial generalization (regionalization), and second, time-series features that are derived from the past time series at the respective well. Moreover, we test random integer features as entity information for comparison. We use a published dataset of 108 groundwater wells in Germany, and evaluate the performance of the models in terms of Nash–Sutcliffe efficiency (NSE) in an in-sample and an out-of-sample setting, representing temporal and spatial generalization. Our results show that entity-aware models work well with a mean performance of NSE >0.8 in an in-sample setting, thus being comparable to, or even outperforming, single-well models. However, they do not generalize well spatially in an out-of-sample setting (mean NSE <0.7, i.e. lower than a global model without entity information). Strikingly, all model variants, regardless of the type of static features used, basically perform equally well both in- and out-of-sample. The conclusion is that the model in fact does not show entity awareness, but uses static features merely as unique identifiers, raising the research question of how to properly establish entity awareness in deep learning models. Potential future avenues lie in bigger datasets, as the relatively small number of wells in the dataset might not be enough to take full advantage of global models. Also, more research is needed to find meaningful static features for ML in hydrogeology.

Element relationship and extension path of clinical evidence knowledge map with Chinese patent medicine

This study aims to construct the element relationship and extension path of clinical evidence knowledge map with Chinese patent medicine, providing basic technical support for the formation and transformation of the evidence chain of Chinese patent medicine and providing collection, induction, and summary schemes for massive and disorganized clinical data. Based on the elements of evidence-based PICOS, the conventional construction methods of knowledge graph were collected and summarized. Firstly, the data entities related to Chinese patent medicine were classified, and entity linking was performed(disambiguation). Secondly, the study associated and classified the attribute information of the data entity. Finally, the logical relationship between entities was constructed, and then the element relationship and extension path of the knowledge map conforming to the characteristics of clinical evidence of Chinese patent medicine were summarized. The construction of the clinical evidence knowledge map of Chinese patent medicine was mainly based on process design and logical structure, and the element relationship of the knowledge map was expressed according to the PICOS principle and evidence level. The extension path crossed three levels(model layer, data layer application, and new evidence application), and the study gradually explored the path from disease, core evaluation indicators, Chinese patent medicine, core prescriptions, syndrome and treatment rules, and medical case comparison(evolution law) to new drug research and development. In this study, the top-level design of the construction of the clinical evidence knowledge map of Chinese patent medicine has been clarified, but it still needs the joint efforts of interdisciplinary disciplines. With the continuous improvement of the map construction technology in line with the characteristics of TCM, the study can provide necessary basic technical support and reference for the development of the TCM discipline.

Feasibility of Applying the OMOP Common Data Model to Traditional Eastern Asian Medicine Dataset.

To evaluate the feasibility of applying the Observational Medical Outcome Partnership (OMOP) Common Data Model (CDM) to databases of traditional East Asian medicine (TEAM), we composed a TEAM dataset and transformed it to the OMOP CDM. We found that some important TEAM information entities could not be transformed to the OMOP CDM (version 6.0) data fields. We suggest to develop data fields and guideline for transforming TEAM data to the OMOP CDM.

Joint extraction model of entity relations based on decomposition strategy

Named entity recognition and relation extraction are two important fundamental tasks in natural language processing. The joint entity-relationship extraction model based on parameter sharing can effectively reduce the impact of cascading errors on model performance by performing joint learning of entities and relationships in a single model, but it still cannot essentially get rid of the influence of pipeline models and suffers from entity information redundancy and inability to recognize overlapping entities. To this end, we propose a joint extraction model based on the decomposition strategy of pointer mechanism is proposed. The joint extraction task is divided into two parts. First, identify the head entity, utilizing the positive gain effect of the head entity on tail entity identification.Then, utilize a hierarchical model to improve the accuracy of the tail entity and relationship identification. Meanwhile, we introduce a pointer model to obtain the joint features of entity boundaries and relationship types to achieve boundary-aware classification. The experimental results show that the model achieves better results on both NYT and WebNLG datasets.

Cyber insurance risk analysis framework considerations

PurposeIn recent years, the frequency and severity of cybersecurity incidents have prompted customers to seek out specialized insurance products. However, this has also presented insurers with operational challenges and increased costs. The assessment of risks for health systems and cyber–physical systems (CPS) necessitates a heightened degree of attention. The significant values of potential damages and claims request a solid insurance system, part of cyber-resilience. This research paper focuses on the emerging cyber insurance market that is currently in the process of standardizing and improving its risk analysis concerning the potential insured entity.Design/methodology/approachThe authors' approach involves a quantitative analysis utilizing a Likert-style questionnaire designed to survey cyber insurance professionals. The authors' aim is to identify the current methods used in gathering information from potential clients, as well as the manner in which this information is analyzed by the insurers. Additionally, the authors gather insights on potential improvements that could be made to this process.FindingsThe study the authors elaborated it has a particularly important cyber and risk components for insurance area, because it addresses a “niche” area not yet proper addressed in specialized literature – cyber insurance. Cyber risk management approaches are not uniform at the international level, nor at the insurer level. Also, not all insurers can perform solid assessments, especially since their companies should first prove that they are fully compliant with international cyber security standards.Research limitations/implicationsThis research has concentrated on analyzing the current practices in terms of gathering information about the insured entity before issuing the cyber insurance policy, level of details concerning the cyber security posture of the insured entity and way such information should be analyzed in a standardized and useful manner. The novelty of this research resides in the analysis performed as detailed above and the proposals in terms of information gathered, depth of analysis and standardization of approach made. Future work on the topic can focus on the standardization process for analyzing cyber risk for insurance clients, to improve the proposal based also on historical elements and trends in the market. Thus, future research can further refine the standardization process to analyze in more depth the way this can be implemented and included in relevant legislation at the EU level.Practical implicationsProposed improvements include proposals in terms of the level of detail and the usefulness of an independent centralized approach for information gathering and analysis, especially given the re-insurance and brokerage activities. The authors also propose a common practical procedural approach in risk management, with the involvement of insurance companies and certification institutions of cyber security auditors.Originality/valueThe study investigates the information gathered by insurers from potential clients of cyber insurance and the way this is analyzed and updated for issuance of the insurance policy.

Construction and Implementation of Tibetan Cultural Relics Question and Answer System Based on Knowledge Graph

Tibet is a region with a long history and culture, with a large number of precious cultural relics resources. In the digital age, building a question-and-answer system based on the Knowledge map of Tibetan cultural relics can better protect and pass on Tibetan cultural heritage. Firstly, the Tibetan cultural relics data were obtained by crawler technology and stored in neo4j database to complete the knowledge graph construction. Secondly, in order to make the system understand the semantic information of the user's question, the bert_bilstm_crf model is used to recognize the entity information of the question, and the bert_textcnn model is used to recognize the intention of the question, and finally the answer result is returned by constructing the cypher query graph.

A Subgraph Retrieval Method for Complex Questions Based on Hybrid Semantics and Path Representation

Current subgraph retrieval methods generally fall into two categories: those that rely on semantic matching, which use only surface-level semantic information of relations and lack flexibility; and those based on personalized PageRank algorithms, which fail to leverage the semantic connection between the relation and the question, rendering them susceptible to noisy data. To address these issues, this paper introduces a novel retrieval model that employs hybrid semantics of relations and path representations. Specifically, hybrid semantics involves merging relational and entity information within a knowledge graph to extract the deep semantics of relations and enhance semantic representation by integrating it with the explicit descriptive text of the relations. Path representation merges the semantics of the current relation with those of preceding ones to form a complete path representation. This representation is then semantically matched with the question to compute a score, which determines whether the relation should form part of the subgraph. We integrated our subgraph retrieval model with the Neural Symbolic Machine (NSM) reasoning model and evaluated it on the publicly available CWQ and WebQSP datasets. The experimental results demonstrate that our method performs exceptionally well on these datasets, validating the efficacy of utilizing deep semantics and path representations for the retrieval of subgraphs in response to complex questions.