Learning Entity Research Articles

MDSEA: Knowledge Graph Entity Alignment Based on Multimodal Data Supervision

With the development of social media, the internet, and sensing technologies, multimodal data are becoming increasingly common. Integrating these data into knowledge graphs can help models to better understand and utilize these rich sources of information. The basic idea of the existing methods for entity alignment in knowledge graphs is to extract different data features, such as structure, text, attributes, images, etc., and then fuse these different modal features. The entity similarity in different knowledge graphs is calculated based on the fused features. However, the structures, attribute information, image information, text descriptions, etc., of different knowledge graphs often have significant differences. Directly integrating different modal information can easily introduce noise, thus affecting the effectiveness of the entity alignment. To address the above issues, this paper proposes a knowledge graph entity alignment method based on multimodal data supervision. First, Transformer is used to obtain encoded representations of knowledge graph entities. Then, a multimodal supervised method is used for learning the entity representations in the knowledge graph so that the vector representations of the entities contain rich multimodal semantic information, thereby enhancing the generalization ability of the learned entity representations. Finally, the information from different modalities is mapped to a shared low-dimensional subspace, making similar entities closer in the subspace, thus optimizing the entity alignment effect. The experiments on the DBP15K dataset compared with methods such as MTransE, JAPE, EVA, DNCN, etc., all achieve optimal results.

Supervised Machine Learning Entity Sentiment Analysis: Prediction of Support for 2024 Indonesian Presidential Candidates

Supervised Machine Learning Entity Sentiment Analysis: Prediction of Support for 2024 Indonesian Presidential Candidates

LAFA: Multimodal Knowledge Graph Completion with Link Aware Fusion and Aggregation

Recently, an enormous amount of research has emerged on multimodal knowledge graph completion (MKGC), which seeks to extract knowledge from multimodal data and predict the most plausible missing facts to complete a given multimodal knowledge graph (MKG). However, existing MKGC approaches largely ignore that visual information may introduce noise and lead to uncertainty when adding them to the traditional KG embeddings due to the contribution of each associated image to entity is different in diverse link scenarios. Moreover, treating each triple independently when learning entity embeddings leads to local structural and the whole graph information missing. To address these challenges, we propose a novel link aware fusion and aggregation based multimodal knowledge graph completion model named LAFA, which is composed of link aware fusion module and link aware aggregation module. The link aware fusion module alleviates noise of irrelevant visual information by calculating the importance between an entity and its associated images in different link scenarios, and fuses the visual and structural embeddings according to the importance through our proposed modality embedding fusion mechanism. The link aware aggregation module assigns neighbor structural information to a given central entity by calculating the importance between the entity and its neighbors, and aggregating the fused embeddings through linear combination according to the importance. Extensive experiments on standard datasets validate that LAFA can obtain state-of-the-art performance.

Edukacja międzykulturowa w Niemczech (na przykładzie działalności ośrodków opieki dziennej Familienzentrum Lebenshilfe Elmshorn)

The article contains considerations on intercultural education in Germany based on the example of Familienzentrum Lebenshilfe Elmshorn day care centres. Against the background of these considerations and referring to the thesis that early intercultural education provides an opportunity to develop lasting competences in the field of broadly understood coexistence, the German concern for intercultural education, care, help and support is presented. The Federal Assisted Living Association in the district of Pinneberg offers initiatives in this area through six integrated day care centres in Elmshorn, Pinneberg, Appen-Etz and Wedel. On the basis of the analysis of the activities undertaken in the city of Elmhorn and in day care centres, integration activities are shown – the ones that take place both in an intercultural perspective and in the family space. The article emphasizes that early intercultural education broadens thinking about education, understanding that a child is a learning entity striving for self-fulfillment, developing their own strength and possibilities in the process of “dialogue” with an adult. Early cultural education is also a path to peaceful coexistence based on mutual knowledge and understanding.

Enhancing on-pitch learning capabilities with data analytics and technologies in elite sports

ABSTRACT Research question: We have explored the utilisation of data analytics and technology in elite sports and the role it plays in enhancing on-pitch learning capabilities. In the competitive, complex, and dynamic professional sports environment, margins are small and critical for the success of a team or club. It is essential for sports organisations to keep learning individually and collectively to strengthen their ability to improve on-pitch. In this paper, we explore how data analytics and technology enable sports teams to develop learning organisation capabilities to add-value on-pitch by increasing their knowledge base. Research methods: Data for this study were gathered through 33 interviews with elite sport industry experts from football (Premier League, Championship), cricket (First Class County Clubs) and rugby (Rugby League). It includes seven sports directors, 12 managers and coaches, six players and former players, six performance analysts, one member of the medical staff, and one sports analytics academic. Results and findings: Our findings add to the understanding of players, coaches, and teams as learning entities, and discuss how they capture and transform data into knowledge with the use of data analytics and technology, which is then utilised to inform on-pitch practices and decision making. We provide a blueprint framework explaining how a sport club can add value on-pitch by achieving a learning organisation status, through the use of data analytics and technology. Implications: This paper contributes towards the continuing discourse regarding data analytics and technology utilisation within the sports industry, in the on-pitch domain. There has been limited academic research published to date on data analytics and technology use in professional sports, particularly with respect to investigating it from a learning organisation theory perspective.

Social world knowledge: Modeling and applications.

Social world knowledge is a key ingredient in effective communication and information processing by humans and machines alike. As of today, there exist many knowledge bases that represent factual world knowledge. Yet, there is no resource that is designed to capture social aspects of world knowledge. We believe that this work makes an important step towards the formulation and construction of such a resource. We introduce SocialVec, a general framework for eliciting low-dimensional entity embeddings from the social contexts in which they occur in social networks. In this framework, entities correspond to highly popular accounts which invoke general interest. We assume that entities that individual users tend to co-follow are socially related, and use this definition of social context to learn the entity embeddings. Similar to word embeddings which facilitate tasks that involve text semantics, we expect the learned social entity embeddings to benefit multiple tasks of social flavor. In this work, we elicited the social embeddings of roughly 200K entities from a sample of 1.3M Twitter users and the accounts that they follow. We employ and gauge the resulting embeddings on two tasks of social importance. First, we assess the political bias of news sources in terms of entity similarity in the social embedding space. Second, we predict the personal traits of individual Twitter users based on the social embeddings of entities that they follow. In both cases, we show advantageous or competitive performance using our approach compared with task-specific baselines. We further show that existing entity embedding schemes, which are fact-based, fail to capture social aspects of knowledge. We make the learned social entity embeddings available to the research community to support further exploration of social world knowledge and its applications.

MARec: A multi-attention aware paper recommendation method

The paper recommender system has provided great convenience for people to obtain knowledge of what they are interested in. Existing recommendation works mainly rely on learning entities’ feature representations (network embedding) from the Heterogeneous Information Networks (HINs) through meta-paths. Most of them suffer from the difficulty of designing and selecting meta-paths in HIN. Moreover, changes in papers’ captive audiences and users’ reading favor in the recent trends are always covered up by long-term trends. To this end, we introduce a multi-attention aware recommendation method, named MARec. Specifically, to efficiently design and select meta-paths, we propose an auxiliary node-driven HIN construction method and combine it with the graph attention network (GAT) to learn the entities’ feature representations. To endow the recommendation results with timeliness, we design an attention-aware Bi-directional LSTM (Bi-LSTM) and a compensation mechanism to incorporate the recent trend changes. Furthermore, to take advantage of the importance of different papers/users, we utilize an attention mechanism to capture their importance by adaptively fusing the interactive historical data of those paper/user entities. We use extensive experiments on three real-world datasets to show that our proposed MARec outperforms current representative baselines by 11.49%, 11.40%, and 13.37% on average on three main metrics.

A confidence-aware and path-enhanced convolutional neural network embedding framework on noisy knowledge graph

In recent years, Knowledge Graphs (KGs) have been widely used in applications such as search engines and Q&A systems. During construction, errors were inevitably introduced and KGs may contain many incorrect facts. However, most KG representation learning methods assume that all triple facts are correct, making KG noise detection a challenge. Although some knowledge representation methods are based on a confidence-aware framework, they are usually limited by the translation assumption in TransE and confidence calculation methods. To address the above problems, we propose a more accurate and effective confidence-aware and path-enhanced convolutional neural network knowledge embedding framework (CPConvKE). It makes use of structural, entity type, and rule information for knowledge graph noise detection and knowledge representation learning simultaneously. Specifically, for representation learning, we introduce a gating-based path embedding method to filter out noise while learning entity and relation embeddings. For the confidence evaluation, we propose a triple confidence estimator that uses entity type and rule information as prior probability and defines posterior probability based on the embedding. We evaluate the effectiveness of our model on the knowledge graph noise detection, completion, and triple classification tasks. The experimental results show that our confidence-aware model achieves significant and consistent improvements on all tasks, which confirms the ability of CPConvKE to detect noise and learn clean embeddings in a noisy knowledge graph.

Leveraging natural language processing to augment structured social determinants of health data in the electronic health record.

Social determinants of health (SDOH) impact health outcomes and are documented in the electronic health record (EHR) through structured data and unstructured clinical notes. However, clinical notes often contain more comprehensive SDOH information, detailing aspects such as status, severity, and temporality. This work has two primary objectives: (1) develop a natural language processing information extraction model to capture detailed SDOH information and (2) evaluate the information gain achieved by applying the SDOH extractor to clinical narratives and combining the extracted representations with existing structured data. We developed a novel SDOH extractor using a deep learning entity and relation extraction architecture to characterize SDOH across various dimensions. In an EHR case study, we applied the SDOH extractor to a large clinical data set with 225089 patients and 430406 notes with social history sections and compared the extracted SDOH information with existing structured data. The SDOH extractor achieved 0.86 F1 on a withheld test set. In the EHR case study, we found extracted SDOH information complements existing structured data with 32% of homeless patients, 19% of current tobacco users, and 10% of drug users only having these health risk factors documented in the clinical narrative. Utilizing EHR data to identify SDOH health risk factors and social needs may improve patient care and outcomes. Semantic representations of text-encoded SDOH information can augment existing structured data, and this more comprehensive SDOH representation can assist health systems in identifying and addressing these social needs.

An explainable framework for drug repositioning from disease information network

Exploring efficient and high-accuracy computational drug repositioning methods has become a popular and attractive topic in drug development. This technology can systematically identify potential drug-disease interactions, which could greatly alleviate the pressures from the high cost and long period taken by traditional drug research and discovery. However, plenty of current computational drug repositioning approaches lack interpretability in predicting drug-disease associations, which will not be friendly to their subsequent in-depth research.To this end, we hereby propose a novel computational framework, called EDEN, for exploring explainable drug repositioning from the disease information network (DIN). EDEN is a graph neural network framework that learns the local semantics and global structure of the DIN, and models the drug-disease associations into the DIN by maximizing the mutual information of both and an end-to-end manner. In this way, the learned biomedical entity and link embeddings are enabled to retain the ability to drug repositioning with the semantical structure of external knowledge, thereby making interpretation possible. Meanwhile, we also propose a matching score based on the final embeddings to generate the predictive drug repositioning explanation. Empirical results on the real-world dataset show that EDEN outperforms other state-of-the-art baselines on most of the metrics. Further studies reveal the effectiveness of the explainability of our approach.

Learning knowledge graph embedding with a dual-attention embedding network

Knowledge Graph Embedding (KGE) aims to retain the intrinsic structural information of knowledge graphs (KGs) via representation learning, which is critical for various downstream tasks including personalized recommendations, intelligent search, and relation extraction. The graph convolutional network (GCN), due to its remarkable performance in modeling graph data, has recently been studied extensively in the KGE field. However, when learning entity representations, most attention-based GCN approaches treat neighborhoods as a whole to measure their importance without considering the direction information of relations. Additionally, these approaches make relation representations perform self-update via a learnable matrix, resulting in ignoring the impact of neighborhood information on representation learning of relations. To this end, this study presents an innovative framework, namely learning knowledge graph embedding with a dual-attention embedding network (D-AEN), to jointly propagate and update the representations of both relations and entities via fusing neighborhood information. Here the dual attentions consist of a bidirectional attention mechanism and a relation-specific attention mechanism for jointly measuring the importance of neighborhoods in respectively learning entity and relation representations. Thus D-AEN enables elements like relations and entities to interact well semantically, which makes their learned representations retain more effective information of KGs. Extensive experimental results on three standard link prediction datasets demonstrate the superiority of D-AEN over several state-of-the-art approaches.

Application of learning organization 2.0: a case study of Ricoh Ena Forest Japan

PurposeThis paper aims to offer an empirical application of the concept of learning organization (LO) 2.0.Design/methodology/approachBased on fieldwork study, a case of Ricoh Ena Forest Project is presented to illustrate the contextualized and multi-stakeholder perspective of LO 2.0 in running an environmental sustainability project.FindingsThe case demonstrated the value of incorporating multiple stakeholders to develop a multi-party learning entity for sustainability pursuit. The findings also highlighted the importance of forfeiting managerial dominance and the creation of a shared commitment in implementing the concept of LO 2.0.Originality/valueThe study adds empirical evidence to the literature on how LO 2.0 can be implemented and provides guidance on tackling some of the potential challenges.

Cross-Temporal Snapshot Alignment for Dynamic Multi-Relational Networks

A dynamic network is often represented as a sequence of snapshots evolving over time. In certain real-world scenarios, the identities of nodes in snapshots of a dynamic network are unknown and need to be figured out. To deal with such a challenge, recently, the task of cross-temporal snapshot alignment for dynamic networks is proposed, which aims to match equivalent nodes across temporal snapshots of a dynamic network given a small set of identified nodes. However, in many dynamic multi-relational networks like temporal knowledge graphs, the relation type information of edges, which can be useful for the alignment task, is neglected by existing methods. In this paper, we focus on a similar task but pay special attention to dynamic multi-relational networks. We propose a Relation-Aware Cross-Temporal Snapshot Alignment model (RCTSA) that incorporates time-dependent topological structure information into temporal node embeddings and temporal relation embeddings. To disentangle time-dependent information and time-independent information of the dynamic multi-relational network, RCTSA maintains a time embedding for each snapshot to preserve the temporal information which is incorporated into entity embeddings and relation embeddings to get the temporal embeddings. After training, the learned entity embeddings of unidentified nodes together with time embeddings can be used for the alignment task. Experimental results on real-world dynamic multi-relational networks demonstrate the effectiveness of our model.

Deep Learning Classification Model for English Translation Styles Introducing Attention Mechanism

Both short-distance association knowledge and long-distance interaction knowledge in the knowledge base contain rich semantics. When learning entity and relation representation in a knowledge base, if we can learn short-distance association knowledge and long-distance interaction knowledge at the same time, we can learn the representation method with rich semantic information and keep the original structure of the knowledge base. Among the knowledge contained in a large number of records, some knowledge reflects individual characteristics and can be called local knowledge; others reflect group characteristics and can be called global knowledge. Using different ways to learn local and global knowledge in the deep learning model will better reflect the difference between the two kinds of knowledge at the model level, and make the model have the ability to understand both individual characteristics and overall characteristics. Through layer-by-layer forward propagation and error back propagation algorithms, the entire network is gradually optimized in an “end-to-end” manner. This “end-to-end” approach leaves some means of introducing prior knowledge flexibly into the model. Although it can reduce the burden on researchers, this “data-driven” approach brings the shortcomings of poor interpretability of learning results and weak generalization ability. Combining the specific prior knowledge implicit in the data with the deep learning algorithm can optimize the algorithm in a targeted manner and avoid blind searching in the solution space, so as to obtain a model with better performance and wider use. To this end, this paper investigates combining prior knowledge with deep learning to design efficient algorithms to address the classification of English translation styles. This paper combines local knowledge with global knowledge and deep learning methods and proposes a memory neural network method combining local knowledge and global knowledge. By recording the local knowledge in the local memory module and simultaneously recording the global knowledge in the global memory module, the method effectively learns the latent information in a large number of records. This paper combines short-distance association knowledge with long-distance interaction knowledge and a distributed representation learning method based on deep learning and proposes a deep learning method combining short-distance association knowledge and long-distance interaction knowledge. On the IWSLT English translation task, experiments show that the method significantly improves translation quality, confirming that grammatical dependencies enhance attention by supplementing dependent grammatical information, resulting in more effective and richer context vectors that more accurately represent contextual situations. Additional experimental analysis showed that the model underwent careful parameter selection and analysis. By mining valuable long-distance interactive knowledge in the knowledge base and using it in the distributed representation learning of the knowledge base, while constraining the short-distance related knowledge and constraining the long-distance interactive knowledge, the learned knowledge can be used to effectively complete the knowledge base distributed representation for discovering new relations.

A Comprehensive Survey on Training Acceleration for Large Machine Learning Models in IoT

The ever-growing artificial intelligence (AI) applications have greatly reshaped our world in many areas, e.g., smart home, computer vision, natural language processing, etc. Behind these applications are usually machine learning (ML) models with extremely large size, which require huge data sets for accurate training to mine the value contained in the big data. Large ML models, however, can consume tremendous computing resources to achieve decent performance and thus, it is difficult to train them in resource-constrained Internet of Things (IoT) environments, which would prevent further development and application of AI techniques in the future. To deal with such challenges, there are many efforts on accelerating the training process for large ML models in IoT. In this article, we provide a comprehensive review on the recent advances toward reducing the computing cost during the training stage while maintaining comparable model accuracy. Specifically, the optimization algorithms that aim to improve the convergence rate are emphasized over various distributed learning architectures that exploit ubiquitous computing resources. Then, the article elaborates the computation hardware acceleration and communication optimization for collaborative training among multiple learning entities. Finally, the remaining challenges, future opportunities, and possible directions are discussed.

Поняття веб-середовища дистанційного навчання

In modern conditions it is necessary to master existing and new learning technologies. Among such technologies, distance learning is important. Participants in the distance learning process need to rethink the learning process in a new format. This involves identifying the main components of the process and new forms of its organization. The main problem, in our opinion, is the lack of many participants in the educational process of the concept of its system. Namely, they have a lack of understanding of the interaction of the constituent elements of distance learning. Therefore, our goal is to provide participants in the educational process with the concept of a single system of distance learning environment. The distance learning web environment is a specific set of conditions, methods and forms of learning. It is also a set of tools for joint distance learning, education and development of students. In addition, the web environment contains the means of interaction of distance learning entities and the means of managing distance learning. At the same time, the interaction between the participants of the educational process provides access to various educational web resources. Educational web resources are information resources that contain a set of specific educational information. The classification of network technologies for working with educational web resources is given. Distance learning tools, which are one of the components of the web environment, are considered. The scheme of the general structure of the web distance learning environment is given. An important place in this structure is occupied by the conditions of distance learning. The list of basic conditions is given. The concept of web-based distance learning as a single system of its components is formulated. It provides for the following conditions: – the educational process must be clearly organized. – the relationship between learning conditions and means should be established. – there must be technical means and possibilities of their use. Therefore, the web-based distance learning environment will be the only system that will enable applicants to receive quality education. Key words: web environment, web resources, distance learning, network learning technologies, web resource format

Learning Entity Linking Features for Emerging Entities

Entity linking (EL) is the process of linking entity mentions appearing in text with their corresponding entities in a knowledge base. EL features of entities (e.g., prior probability, relatedness score, and entity embedding) are usually estimated based on Wikipedia. However, for newly emerging entities (EEs) which have just been discovered in news, they may still not be included in Wikipedia yet. As a consequence, it is unable to obtain required EL features for those EEs from Wikipedia and EL models will always fail to link ambiguous mentions with those EEs correctly as the absence of their EL features. To deal with this problem, in this paper we focus on a new task of learning EL features for emerging entities in a general way. We propose a novel approach called STAMO to learn high-quality EL features for EEs automatically, which needs just a small number of labeled documents for each EE collected from the Web, as it could further leverage the knowledge hidden in the unlabeled data. STAMO is mainly based on self-training, which makes it flexibly integrated with any EL feature or EL model, but also makes it easily suffer from the error reinforcement problem caused by the mislabeled data. Instead of some common self-training strategies that try to throw the mislabeled data away explicitly, we regard self-training as a multiple optimization process with respect to the EL features of EEs, and propose both intra-slot and inter-slot optimizations to alleviate the error reinforcement problem implicitly. We construct two EL datasets involving selected EEs to evaluate the quality of obtained EL features for EEs, and the experimental results show that our approach significantly outperforms other baseline methods of learning EL features.

Teaching Method for Entity–Relationship Models Based on Semantic Network Theory

Students in database courses often have difficulty learning entity–relationship (ER) modeling. According to semantic network theory, learning to construct an ER diagram for a database problem requires complex semantic transformations between the problem and the diagram. Such complex transformation may require excessive mental effort by learners, jeopardizing their learning outcomes. A concept map is a learning tool that incorporates elements of both learning theory and semantic network theory. In this study, concept maps were used to describe the semantic transformation process to increase learner understanding of ER modeling. An empirical experiment was conducted on two database courses (one concept-map-based and one conventional course) to examine the effect of using concept maps on understanding ER modeling according to cognitive load theory. The experimental results revealed that the concept-map-based teaching method was superior to the conventional teaching method because it improved mental efficiency by reducing extraneous load while increasing germane load. Moreover, concept maps can be used as a medium to facilitate communication regarding ER modeling problems between learners and instructors, thereby improving learning efficiency. The results can help educators and researchers understand the effectiveness of concept maps for ER model learning, motivate them to resolve learning difficulties, and encourage them to develop improved teaching methods by using semantic network theory.

HAMLET: A Hierarchical Agent-based Machine Learning Platform

Hierarchical Multi-agent Systems provide convenient and relevant ways to analyze, model, and simulate complex systems composed of a large number of entities that interact at different levels of abstraction. In this article, we introduce HAMLET (Hierarchical Agent-based Machine LEarning plaTform), a hybrid machine learning platform based on hierarchical multi-agent systems, to facilitate the research and democratization of geographically and/or locally distributed machine learning entities. The proposed system models machine learning solutions as a hypergraph and autonomously sets up a multi-level structure of heterogeneous agents based on their innate capabilities and learned skills. HAMLET aids the design and management of machine learning systems and provides analytical capabilities for research communities to assess the existing and/or new algorithms/datasets through flexible and customizable queries. The proposed hybrid machine learning platform does not assume restrictions on the type of learning algorithms/datasets and is theoretically proven to be sound and complete with polynomial computational requirements. Additionally, it is examined empirically on 120 training and 4 generalized batch testing tasks performed on 24 machine learning algorithms and 9 standard datasets. The provided experimental results not only establish confidence in the platform’s consistency and correctness but also demonstrate its testing and analytical capacity.

Information extraction for different layouts of invoice images

ABSTRACT In the organization, they purchased goods or services from different suppliers and used invoice documents to confirm the payment. The invoice documents contained information that can be used for a business decision but, the process of information extraction required many resources to collect the data. The traditional way used template matching-based methods. This process identifies the parts on an image that match a predefined template and requires new manual annotation when processing the new image layout. Therefore, developing a system for robustly extracting entities from different layouts of invoices is necessary. Existing research applied deep learning and Name Entity Recognition (NER) for information extraction but, extracting invoice information was widely done in English and Chinese languages. In this study, we constructed a deep learning model using BiLSTM-CRF (Bidirectional Long Short-Term Memory-Conditional Random Fields) with word and character embedding for information extraction from different layouts of Thai invoice images. The model was evaluated by Semantic Evaluation at a full named-entity level. Our experimental results showed that this method can achieve a precision of 0.9557, recall of 0.9486, and F1-score of 0.9521 for the partial match; precision of 0.9329, recall of 0.9259, and F1-score of 0.9294 for the exact match and the result of the F1-score was significantly influenced by the quality of images and text result from Optical Character Recognition (OCR). Abbreviations: BERT: bidirectional encoder representations from transformers; BiLSTM: bidirectional long short-term memory; COR: correct; CRF: conditional random fields; CV: computer vision; ELMO: embeddings from language model; INC: incorrect; MIS: missing; MSE: mean squared error; MUC: message understanding conference; NER: named entity recognition; NLP: natural language processing; OCR: optical character recognition; PAR: partial; SemEval: semantic evaluation; SPU: spurius