Description Of Entities Research Articles

Applying Interval Fuzzy Petri Net to Failure Analysis

In this article, the authors propose a new approach for modelling and failure analysis by combining the graphical representation provided by Petri nets and fuzzy logic. The graphical method is used for describing the relationship between conditions and events. The use of Petri nets in failure analysis enables replacing logic gate functions in fault trees. The Fuzzy logic technique allows natural language descriptions of process entities as well as an if-then rule-based definition of production. In addition, this study devises an alternative, a trapezoidal graph method in order to account for failure scenarios. Examples validating this novel method in dealing with failure analysis are also provided.

Patient Similarity via Joint Embeddings of Medical Knowledge Graph and Medical Entity Descriptions

With the prevalence and growing volume of Electronic Health Records (EHRs), there has been increasing interest in mining EHRs for improving clinical decision support. The accurate identification of patients with similar conditions based on EHRs is a key step in personalized healthcare. Existing studies model EHRs by medical knowledge graph embedding to learn the latent embeddings of medical entities (e.g., patients, medications, diagnoses and procedures). However, such precisely structured data is usually limited in quantity and in scope. Therefore, to enhance the quality of the embeddings it is important to consider more widely available medical information such as medical entity descriptions. In this paper we propose a novel framework, called Deep Patient Similarity (DeepPS). Specifically, DeepPS incorporates medical entity descriptions by augmenting the embeddings of medical entities and relations with the embeddings of words, which leverages both information from medical knowledge graph structures and the contexts of medical entity descriptions. Furthermore, DeepPS employs the embeddings to patient similarity learning by leveraging Siamese Convolutional Neural Network (CNN) with Spatial Pyramid Pooling (SPP). Extensive experiments on real datasets are conducted to show superior performance of our proposed framework.

A Heterogeneous Battlefield Situation Information Sharing Method Based on Content

Various information systems adopt different information category standards and description methods even for the same battlefield space. This leads to the heterogeneity of information distributed in different systems, which hinders the information sharing among different systems. In this paper, we adopt the idea of schema mapping and design a framework of realizing heterogeneous information sharing based on content. We design a concept-logic tree model to organize the battlefield situation information and realize the mapping from local concept models in different systems to a global unified concept model. By constructing a unified information space, we realize the centralized organization, storage, and management of entity description information. Then, the information broadcasting mechanism and content based information query mechanism are designed to realize information sharing. Theoretical analysis and experiment results verify the effectiveness of the proposed framework.

Teorijski i praktični aspekti upravljanja relacijama u suvremenoj arhivskoj teoriji i praksi

Arhivski stručnjaci u svojem radu definiraju i koriste se mnoštvom relacija na različite načine. U konkretnim situacijama različito ih razumiju i različito primjenjuju. Od usvajanja prvoga međunarodnog arhivskog standarda ISAD(G), pojam relacije sustavno je ugrađen u opis arhivskih entiteta i zato ga svi koji se bave opisom moraju razumjeti u skladu sa svrhom standarda. U prilogu su predstavljeni teorijski okviri uporabe relacija u različitim kontekstima, koji se temelje na arhivskim standardima. Relacije su kvantitativno definirane, prije svega među krovnim arhivskim entitetima. Sve veća složenost upravljanja krovnim arhivskim entitetima zahtijeva razmjerno veći intelektualni napor arhivskih stručnjaka u odnosu na nestandardizirana rješenja u opisu arhivskih entiteta. U tom će kontekstu biti potrebno razmišljati o rješenjima koje poznajemo pod nazivom umjetna inteligencija.

Knowledge graph based natural language generation with adapted pointer-generator networks

Pointer-generator networks have recently shown superior performance in Natural Language Generation (NLG) tasks, such as automatic generating descriptions for entities in Knowledge Graph (KG). In the absence of the introductory description about an entity we intend to know, the natural language text automatically generated by neural network model can greatly help people to better understand the entity. Entities in KG always have multiple property fields and corresponding values. The target generated description sentences should consist of these slot types and slot values in a consistent and high coverage manner. In order to cover the facts in an input KG, pointer-generator networks always copy certain segments from the input sequences via softmax pointing while generating novel words through the generator. But the challenges that when and where to integrate the copied information with the generated one, how to prevent duplicate generation and information loss are hard to conquer. In this paper, the KG2TEXT model based on adapted pointer-generator networks is proposed. In it, a varied coverage loss function is devised to cover attribute-value pairs as many as possible when generating natural language descriptions for entities in KG. Secondly, an attention mechanism named supervised attention mechanism is added to the model which aims to guide the soft switch transformation process (to generate or to copy). With empirical experiments on two kinds of realistic datasets, the KG2TEXT model achieves promising results and outperforms the state-of-the-art approaches.

Embedding Learning with Triple Trustiness on Noisy Knowledge Graph

Embedding learning on knowledge graphs (KGs) aims to encode all entities and relationships into a continuous vector space, which provides an effective and flexible method to implement downstream knowledge-driven artificial intelligence (AI) and natural language processing (NLP) tasks. Since KG construction usually involves automatic mechanisms with less human supervision, it inevitably brings in plenty of noises to KGs. However, most conventional KG embedding approaches inappropriately assume that all facts in existing KGs are completely correct and ignore noise issues, which brings about potentially serious errors. To address this issue, in this paper we propose a novel approach to learn embeddings with triple trustiness on KGs, which takes possible noises into consideration. Specifically, we calculate the trustiness value of triples according to the rich and relatively reliable information from large amounts of entity type instances and entity descriptions in KGs. In addition, we present a cross-entropy based loss function for model optimization. In experiments, we evaluate our models on KG noise detection, KG completion and classification. Through extensive experiments on three datasets, we demonstrate that our proposed model can learn better embeddings than all baselines on noisy KGs.

Rule-driven inconsistency resolution for knowledge graph generation rules

Knowledge graphs, which contain annotated descriptions of entities and their interrelations, are often generated using rules that apply semantic annotations to certain data sources. (Re)using ontology terms without adhering to the axioms defined by their ontologies results in inconsistencies in these graphs, affecting their quality. Methods and tools were proposed to detect and resolve inconsistencies, the root causes of which include rules and ontologies. However, these either require access to the complete knowledge graph, which is not always available in a time-constrained situation, or assume that only generation rules can be refined but not ontologies. In the past, we proposed a rule-driven method for detecting and resolving inconsistencies without complete knowledge graph access, but it requires a predefined set of refinements to the rules and does not guide users with respect to the order the rules should be inspected. We extend our previous work with a rule-driven method, called Resglass, that considers refinements for generation rules as well as ontologies. In this article, we describe Resglass, which includes a ranking to determine the order with which rules and ontology elements should be inspected, and its implementation. The ranking is evaluated by comparing the manual ranking of experts to our automatic ranking. The evaluation shows that our automatic ranking achieves an overlap of 80% with experts ranking, reducing this way the effort required during the resolution of inconsistencies in both rules and ontologies.

Fifty years of thyroid pathology: concepts and developments

The past half century has seen a number of advances in pathology of thyroid diseases, especially neoplastic lesions. These include the description of new entities, the definition of prognostically important lesions, the incorporation of fine needle aspiration biopsy and its functional risk stratification of diagnoses into the clinical evaluation and therapeutic recommendations of the patient with thyroid nodules and the understanding of thyroid neoplastic development, diagnostic and prognostic parameters by use of molecular analysis so that such techniques are becoming standard of care for patients with thyroid tumors. The histopathologist and cytopathologist have been and continue to be at the forefront in the definition and understanding of these areas of thyroid disease. This review describes many of the most important advances in this area in an attempt bring the practicing pathologist up to date in these developments.

Sovereignty, Mastery, and Law in the Danish West Indies, 1672–1733

AbstractIn the late seventeenth and early eighteenth centuries, officers of the Danish West India and Guinea Company struggled to balance the sovereignty of the company with the mastery of St. Thomas’ and St. John's slave owners. This struggle was central to the making of the laws that controlled enslaved Africans and their descendants. Slave laws described slave crime and punishment, yet they also contained descriptions of the political entities that had the power to represent and execute the law. Succeeding governors of St. Thomas and St. John set out to align claims about state sovereignty with masters’ prerogatives, and this balancing act shaped the substance of slave law in the Danish West Indies. Indeed, the slave laws pronounced by and the legal thinking engaged in by island governors suggest that sovereignty was never a stable state of affairs in the Danish West Indies. It was always open to renegotiation as governors, with varying degrees of loyalty to the company and at times with questionable capability, strove to determine what sovereignty ought to look like in a time of slavery.

A Review of Machine Learning Applications in Semantic Web

In recent years, the rapid growth of the semantic web has encouraged the use of knowledge graphs to store and exchange data among computers. The change in data storage and retrieval has imposed the need to integrate other techniques that interact with these data. Machine Learning (ML) is the most important fields of study that interacts with data, to extract the patterns and relations that can be used in future applications. However, these techniques are implemented to be used with structured data, where each data instance is characterized using a set of predefined features. Thus, to apply machine learning techniques to knowledge graphs, it is important to convert the formation of the information in these graphs. The knowledge graph represents a collection of interconnected descriptions of entities (objects, events, situations, or abstract concepts in the real world). This work reviews the knowledge graphs and how they are structured and stored. Then, the techniques being used to employ machine learning technique to improve the knowledge graphs are illustrated. Additionally, the integration of the information in the knowledge graphs, so that, they can be used in machine learning techniques are also reviewed. This review can provide a rigid overview for future researchers to provide more attention on the main drawbacks in the existing techniques. Moreover, the review shows that the existing integration approaches limit the performance of the machine learning techniques, as the knowledge extracted from the knowledge graph is trimmed to match the requirements of the ML technique. In conclusion, new machine learning techniques that can extract knowledge directly from the knowledge graph can provide significantly better performance. Keywords: Machine learning, Knowledge graph, Semantic web, Classification, Clustering DOI: 10.7176/JSTR/5-8-01

Roles of Ontologies in Cartography

Roles of Ontologies in Cartography

Wybrane aspekty z historii i filozofii medycyny z uwzględnieniem zagadnień medycyny rodzinnej i aptekarstwa

Considering the issues of family medicine, it is worth noting that only few medical textbooks help understand what medicine is all about. Usually, after a brief discussion of the clinical evaluation of the patient's condition, or the doctor-patient relationship, detailed descriptions of specific disease entities are presented. Family medicine is a branch of medicine devoted to comprehensive health care for all family members who are under the care of a family practitioner. A holistic approach to the patient (also in pharmacies) is an important direction of modern medicine. A common counter-argument of the scientific view of medicine is the suggestion that it leads to the dehumanisation of medicine and limits the holistic view of the patient. These concerns are not justified as long as interdisciplinary approach is considered, which is an important aspect of family medicine. This field of medicine, the target of which is to guarantee comprehensive medical care to all family members under the care of a family practitioner, addresses the holistic approach to the patient, which is an important direction of modern medicine.

Recurrent neural networks with segment attention and entity description for relation extraction from clinical texts.

At present, great progress has been achieved on the relation extraction for clinical texts, but we have noticed that the current models have great drawbacks when dealing with long sentences and multiple entities in a sentence. In this paper, we propose a novel neural network architecture based on Bidirectional Long Short-Term Memory Networks for relation classification. Firstly, we utilize a concat-attention mechanism for capturing the most important context words for relation extraction in a sentence. In addition, a segment attention mechanism is proposed to improve the performance of the model processing long sentences. Finally, a tensor-based entity description is used to overcome the performance degradation of the model when there are multiple entities in a sentence. The performance of the proposed model is evaluated on a part of the i2b2-2010 shared task clinical relation extraction dataset. The result indicates that our model can effectively overcome the above two problems and improve the F1-score by approximately 3% compared with baseline model.

Relation prediction in knowledge graph by Multi-Label Deep Neural Network

Knowledge graph will be usefull for the intelligent system. As the relationship prediction on the knowledge graph becomes accurate, construction of a knowledge graph and detection of erroneous information included in a knowledge graph can be performed more conveniently. The goal of our research is to predict a relation (predicate) of two given Knowledge Graph (KG) entities (subject and object). Link prediction between entities is important for developing large-scale ontologies and for KG completion. TransE and TransR have been proposed as the methods for such a prediction. However, TransE and TransR embed both entities and relations in the same (or different) semantic space(s). In this research we propose a simple architecture model with emphasis on relation prediction by using a Multi-Label Deep Neural Network (DNN), and developed KGML. KGML embeds entities only; given subject and object are embedded and concatenated to predict probability distribution of predicates. Since the output of KGML is the probability distribution in [0, 1], output can be classified as positive and negative by using the threshold of 0.5. Since the output of the existing method TransE is the score in [0, ∞), the threshold value must be calculated each time. Experimental results showed that predictions by KGML are more accurate than those by TransE and TransR. KGML is more accurate than DKRL which uses both KG triples and entity descriptions for learning. KGML is more accurate than PTransE in and its learning speed is faster than PTransE. The code of KGML is available at https://github.com/yo0826jp/KGML.

Entity Linking via Symmetrical Attention-Based Neural Network and Entity Structural Features

In the process of knowledge graph construction, entity linking is a pivotal step, which maps mentions in text to a knowledge base. Existing models only utilize individual information to represent their latent features and ignore the correlation between entities and their mentions. Besides, in the process of entity feature extraction, only partial latent features, i.e., context features, are leveraged to extract latent features, and the pivotal entity structural features are ignored. In this paper, we propose SA-ESF, which leverages the symmetrical Bi-LSTM neural network with the double attention mechanism to calculate the correlation between mentions and entities in two aspects: (1) entity embeddings and mention context features; (2) mention embeddings and entity description features; furthermore, the context features, structural features, and entity ID feature are integrated to represent entity embeddings jointly. Finally, we leverage (1) the similarity score between each mention and its candidate entities and (2) the prior probability to calculate the final ranking results. The experimental results on nine benchmark dataset validate the performance of SA-ESF where the average F1 score is up to 0.866.

Phytochemical characterization and comparative studies of four Cecropia species collected in Panama using multivariate data analysis

Plant species of the genus Cecropia (Urticaceae) are used as traditional medicine in Latin-America, and are commercially available as food supplements. The aim of this study was to characterize and compare the phytochemical constituents of four Cecropia species collected in Panama. The structures of 11 compounds isolated from leaves of C. obtusifolia were elucidated based on high resolution mass spectrometry (HRMS) and nuclear magnetic resonance (NMR) spectroscopic analysis; the polyphenolic constituents of leaves of all four Cecropia species and commercial products were characterized using high performance liquid chromatography-diode array detection-quadrupole time of flight-tandem high resolution mass spectrometry (HPLC-DAD-QTOF). Forty-seven compounds were fully identified or tentatively characterized. Thirty-nine of these have not been previously reported for the species under investigation. Multivariate analysis revelead that C. obtusifolia and C. insignis are the most related species, while C. hispidissima is the most segregated one. Considering the importance of the description of novel chemical entities and the increasing interest and use of natural products, this study may be of great help for chemotaxonomic purposes, the interpretation of medicinal properties and for quality assessment of herbal supplements containing Cecropia leaves.

Attention-Based Joint Entity Linking with Entity Embedding

Entity linking (also called entity disambiguation) aims to map the mentions in a given document to their corresponding entities in a target knowledge base. In order to build a high-quality entity linking system, efforts are made in three parts: Encoding of the entity, encoding of the mention context, and modeling the coherence among mentions. For the encoding of entity, we use long short term memory (LSTM) and a convolutional neural network (CNN) to encode the entity context and entity description, respectively. Then, we design a function to combine all the different entity information aspects, in order to generate unified, dense entity embeddings. For the encoding of mention context, unlike standard attention mechanisms which can only capture important individual words, we introduce a novel, attention mechanism-based LSTM model, which can effectively capture the important text spans around a given mention with a conditional random field (CRF) layer. In addition, we take the coherence among mentions into consideration with a Forward-Backward Algorithm, which is less time-consuming than previous methods. Our experimental results show that our model obtains a competitive, or even better, performance than state-of-the-art models across different datasets.

Knowledge representation learning with entity descriptions, hierarchical types, and textual relations

Knowledge representation learning methods usually only utilize triple facts, or just consider one kind of extra information. In this paper, we propose a multi-source knowledge representation learning (MKRL) model, which can combine entity descriptions, hierarchical types, and textual relations with triple facts. Specifically, for entity descriptions, a convolutional neural network is used to get representations. For hierarchical type, weighted hierarchy encoders are used to construct the projection matrixes of hierarchical types, and the projection matrix of an entity combines all hierarchical type projection matrixes of the entity with the relation-specific type constrains. For textual relations, a sentence-level attention mechanism is employed to get representations. We evaluate MKRL model on knowledge graph completion task with dataset FB15k-237, and experimental results demonstrate that our model outperforms the state-of-the-art methods, which indicates the effectiveness of multi-source information for knowledge representation.

Self-organised criticality and emergent hyperbolic networks: blueprint for complexity in social dynamics

Online social dynamics based on human endeavours exhibit prominent complexity in the emergence of new features embodied in the appearance of collective social values. The vast amount of empirical data collected at various websites provides a unique opportunity for the quantitative study of the underlying social dynamics in full analogy with complex systems in the physics laboratory. Here, we briefly describe the extent of these analogies and indicate the methods from other science disciplines that the physics theory can incorporate in order to provide an adequate description of human entities and principles of their self-organisation. We demonstrate the approach on two examples using empirical data regarding knowledge-creation processes in online chats and questions-and-answers. Specifically, we describe the self-organised criticality as the acting mechanism in the social knowledge-sharing dynamics and demonstrate the emergence of the hyperbolic geometry of the co-evolving networks that underlie these stochastic processes.

Knowledge Graph Embedding With Interactive Guidance From Entity Descriptions

Knowledge Graph (KG) embedding aims to represent both entities and relations into a continuous low-dimensional vector space. Most previous attempts perform the embedding task using only knowledge triples to indicate relations between entities. Entity descriptions, although containing rich background information, have not been well utilized in these methods. In this paper, we propose Entity Descriptions-Guided Embedding (EDGE), a novel method for learning the knowledge graph representations with semantic guidance from entity descriptions. EDGE enables an embedding model to learn simultaneously from 1) knowledge triples that have been directly observed in a given KG, and 2) entity descriptions which have rich semantic information about these entities. In the learning process, EDGE encodes the semantics of entity descriptions to enhance the learning of knowledge graph embedding, and integrates such learned KG embedding to constraint their corresponding word embeddings in entity descriptions. Through this interactive procedure, semantics of entity descriptions may be better transferred into the learned KG embedding. We evaluate EDGE in link prediction and entity classification on Freebase and WordNet. Experimental results show that: 1) with entity descriptions injected, EDGE achieves significant and consistent improvements over state-of-the-art baselines; and 2) compared to those one-time injection schemes studied before, the interactive guidance strategy maximizes the utility of entity descriptions for KG embedding, and indeed achieves substantially better performance.