Large-scale Entity Research Articles

XLORE 3: A Large-scale Multilingual Knowledge Graph from Heterogeneous Wiki Knowledge Resources

In recent years, Knowledge Graph (KG) has attracted significant attention from academia and industry, resulting in the development of numerous technologies for KG construction, completion, and application. XLORE is one of the largest multilingual KGs built from Baidu Baike and Wikipedia via a series of knowledge modelling and acquisition methods. In this paper, we utilize systematic methods to improve XLORE’s data quality and present its latest version, XLORE 3, which enables the effective integration and management of heterogeneous knowledge from diverse resources. Compared with previous versions, XLORE 3 has three major advantages: 1) We design a comprehensive and reasonable schema, namely XLORE ontology, which can effectively organize and manage entities from various resources. 2) We merge equivalent entities in different languages to facilitate knowledge sharing. We provide a large-scale entity linking system to establish the associations between unstructured text and structured KG. 3) We design a multi-strategy knowledge completion framework, which leverages pre-trained language models and vast amounts of unstructured text to discover missing and new facts. The resulting KG contains 446 concepts, 2,608 properties, 66 million entities, and more than 2 billion facts. It is available and downloadable online 1 , providing a valuable resource for researchers and practitioners in various fields.

Can development of large scale agricultural business entities improve agricultural total factor productivity in China?: an empirical analysis

Large scale agricultural business entities (hereinafter referred to as “the large scale entities”) are newly sprouted in the process of China’s agricultural transformation from traditional production to modern mode, while the improvement of agricultural total factor productivity is an important driving force to realize agricultural transformation in China. Therefore, it is of great significance to explore whether the former has a promoting effect on the latter. First of all, the effective improvement of agricultural total factor productivity by the large scale entity development is analyzed from the two aspects of scale effect and technology utilization effect, and the effect mechanism is discussed in depth in this paper. Secondly, empirical test was carried out by using the panel data of prefecture-level cities from 2015 to 2020. The benchmark regression results show that the development of large scale entities can significantly improve agricultural total factor productivity. The mechanism test results indicate that the development of large scale entities improves the agricultural total factor productivity by raising the agricultural mechanization level. The results of heterogeneity analysis show that the difference between large scale entities would affect the benchmarking results. Therefore, it is believed through the study as discussed in this paper that devoting greater effort to support the development of large scale entities is an important measure to improve agricultural total factor productivity and promote China’s agricultural transformation, but it is necessary to act according to local conditions based on the difference of entity types in the process.

Framework for entity extraction with verification: application to inference of data set usage in research publications

PurposeThe purpose of this paper is to propose an extensible framework for extracting data set usage from research articles.Design/methodology/approachThe framework uses a training set of manually labeled examples to identify word features surrounding data set usage references. Using the word features and general entity identifiers, candidate data sets are extracted and scored separately at the sentence and document levels. Finally, the extracted data set references can be verified by the authors using a web-based verification module.FindingsThis paper successfully addresses a significant gap in entity extraction literature by focusing on data set extraction. In the process, this paper: identified an entity-extraction scenario with specific characteristics that enable a multiphase approach, including a feasible author-verification step; defined the search space for word feature identification; defined scoring functions for sentences and documents; and designed a simple web-based author verification step. The framework is successfully tested on 178 articles authored by researchers from a large research organization.Originality/valueWhereas previous approaches focused on completely automated large-scale entity recognition from text snippets, the proposed framework is designed for a longer, high-quality text, such as a research publication. The framework includes a verification module that enables the request validation of the discovered entities by the authors of the research publications. This module shares some similarities with general crowdsourcing approaches, but the target scenario increases the likelihood of meaningful author participation.

Solving Sensor Ontology Metamatching Problem with Compact Flower Pollination Algorithm

To implement co-operation among applications on the Internet of Things (IoT), we need to describe the meaning of diverse sensor data with the sensor ontology. However, there exists a heterogeneity issue among different sensor ontologies, which hampers their communications. Sensor ontology matching is a feasible solution to this problem, which is able to map the identical ontology entity pairs. This work investigates the sensor ontology meta-matching problem, which indirectly optimizes the sensor ontology alignment’s quality by tuning the weights to aggregate different ontology matchers. Due to the largescale entity and their complex semantic relationships, swarm intelligence (SI) based techniques are emerging as a popular approach to optimize the sensor ontology alignment. Inspired by the success of the flower pollination algorithm (FPA) in the IoT domain, this work further proposes a compact FPA (CFPA), which introduces the compact encoding mechanism to improve the algorithm’s efficiency, and on this basis, the compact exploration and exploitation operators are proposed, and an adaptive switching probability is presented to trade-off these two searching strategies. The experiment uses the ontology alignment evaluation initiative (OAEI)’s benchmark and the real sensor ontologies to test CFPA’s performance. The statistical comparisons show that CFPA significantly outperforms other state-of-the-art sensor ontology matching techniques.

Linking Entities from Text to Hundreds of RDF Datasets for Enabling Large Scale Entity Enrichment

There is a high increase in approaches that receive as input a text and perform named entity recognition (or extraction) for linking the recognized entities of the given text to RDF Knowledge Bases (or datasets). In this way, it is feasible to retrieve more information for these entities, which can be of primary importance for several tasks, e.g., for facilitating manual annotation, hyperlink creation, content enrichment, for improving data veracity and others. However, current approaches link the extracted entities to one or few knowledge bases, therefore, it is not feasible to retrieve the URIs and facts of each recognized entity from multiple datasets and to discover the most relevant datasets for one or more extracted entities. For enabling this functionality, we introduce a research prototype, called LODsyndesisIE, which exploits three widely used Named Entity Recognition and Disambiguation tools (i.e., DBpedia Spotlight, WAT and Stanford CoreNLP) for recognizing the entities of a given text. Afterwards, it links these entities to the LODsyndesis knowledge base, which offers data enrichment and discovery services for millions of entities over hundreds of RDF datasets. We introduce all the steps of LODsyndesisIE, and we provide information on how to exploit its services through its online application and its REST API. Concerning the evaluation, we use three evaluation collections of texts: (i) for comparing the effectiveness of combining different Named Entity Recognition tools, (ii) for measuring the gain in terms of enrichment by linking the extracted entities to LODsyndesis instead of using a single or a few RDF datasets and (iii) for evaluating the efficiency of LODsyndesisIE.

The tumor therapy landscape of synthetic lethality

Synthetic lethality is emerging as an important cancer therapeutic paradigm, while the comprehensive selective treatment opportunities for various tumors have not yet been explored. We develop the Synthetic Lethality Knowledge Graph (SLKG), presenting the tumor therapy landscape of synthetic lethality (SL) and synthetic dosage lethality (SDL). SLKG integrates the large-scale entity of different tumors, drugs and drug targets by exploring a comprehensive set of SL and SDL pairs. The overall therapy landscape is prioritized to identify the best repurposable drug candidates and drug combinations with literature supports, in vitro pharmacologic evidence or clinical trial records. Finally, cladribine, an FDA-approved multiple sclerosis treatment drug, is selected and identified as a repurposable drug for treating melanoma with CDKN2A mutation by in vitro validation, serving as a demonstrating SLKG utility example for novel tumor therapy discovery. Collectively, SLKG forms the computational basis to uncover cancer-specific susceptibilities and therapy strategies based on the principle of synthetic lethality.

Large-scale entity representation learning for biomedical relationship extraction.

The automatic extraction of published relationships between molecular entities has important applications in many biomedical fields, ranging from Systems Biology to Personalized Medicine. Existing works focused on extracting relationships described in single articles or in single sentences. However, a single record is rarely sufficient to judge upon the biological correctness of a relation, as experimental evidence might be weak or only valid in a certain context. Furthermore, statements may be more speculative than confirmative, and different articles often contradict each other. Experts therefore always take the complete literature into account to take a reliable decision upon a relationship. It is an open research question how to do this effectively in an automatic manner. We propose two novel relation extraction approaches which use recent representation learning techniques to create comprehensive models of biomedical entities or entity-pairs, respectively. These representations are learned by considering all publications from PubMed mentioning an entity or a pair. They are used as input for a neural network for classifying relations globally, i.e. the derived predictions are corpus-based, not sentence- or article based as in prior art. Experiments on the extraction of mutation-disease, drug-disease and drug-drug relationships show that the learned embeddings indeed capture semantic information of the entities under study and outperform traditional methods by 4-29% regarding F1 score. Source codes are available at: https://github.com/mariosaenger/bio-re-with-entity-embeddings. Supplementary data are available at Bioinformatics online.

Boosting the Efficiency of Large-Scale Entity Resolution with Enhanced Meta-Blocking

Entity Resolution constitutes a quadratic task that typically scales to large entity collections through blocking. The resulting blocks can be restructured by Meta-blocking to raise precision at a limited cost in recall. At the core of this procedure lies the blocking graph, where the nodes correspond to entities and the edges connect the comparable pairs. There are several configurations for Meta-blocking, but no hints on best practices. In general, the node-centric approaches are more robust and suitable for a series of applications, but suffer from low precision, due to the large number of unnecessary comparisons they retain. In this work, we present three novel methods for node-centric Meta-blocking that significantly improve precision. We also introduce a pre-processing method that restricts the size of the blocking graph by removing a large number of noisy edges. As a result, it reduces the overhead time of Meta-blocking by 2 to 5 times, while increasing precision by up to an order of magnitude for a minor cost in recall. The same technique can be applied as graph-free Meta-blocking, enabling for the first time Entity Resolution over very large datasets even on commodity hardware. We evaluate our approaches through an extensive experimental study over 19 voluminous, established datasets. The outcomes indicate best practices for the configuration of Meta-blocking and verify that our techniques reduce the resolution time of state-of-the-art methods by up to an order of magnitude.

"Driving curiosity in search with large-scale entity networks" by Ilaria Bordino, Mounia Lalmas, Yelena Mejova, and Olivier Van Laere with Martin Vesely as coordinator

In many search scenarios, users sometimes find unexpected, yet interesting and useful results, which make them curious; they experience serendipity. This curiosity encourages them to explore further. We developed an entity search system designed to support such an experience. The system explores the potential of entities extracted from two of the most popular sources of user-generated content -- Wikipedia, a user-curated online encyclopedia, and Yahoo Answers, a more unconstrained question & answering forum -- in promoting serendipitous search. The content of each data source is represented as a large network of entities, enriched with metadata about sentiment, writing quality, and topical category. A lazy random walk with restart is implemented to retrieve entities from the networks for a given entity query. This paper discusses our work, focusing on our experience in designing, developing, and evaluating such a system. We also discuss the challenges in developing large-scale systems that aim to drive curiosity in search.

Off-Line and User-Oriented Approach for Supplier Selection in Dynamic Environment: A Case Study in the Healthcare Services

Evaluating and selecting supplies are critical activities in the process of purchasing and supplying materials. Many manufacturing and service organizations operate in a constantly changing business environment and occasionally have to reconsider their steps in terms of supplier selection. This paper offers a methodology that takes into account the impact of a dynamic business environment on the supplier selection process. This methodology represents an applicable tool supported by decision for the planned selection of a single supplier that changes with time out of a supplier group over a finite planning horizon. The suggested methodology has been tested in a large Israeli organization-Clalit Health Services, which comprises large-scale logistical entity working with hundreds of suppliers on an ongoing basis. Our analysis of application results shows that the suggested strategy of switching suppliers over a predefined planning horizon according to the business environment forecast is over 10% more efficient compared to a strategy that does not change the leading supplier throughout the planning horizon. This average improvement is translated into expected efficiency gains on most operative dimensions which represent selection parameters, such as cost per unit, supply lead-time, reputation and more. Nevertheless, some of their value is lost due to some dimensions.

Special Issue: Simulation Methodologies For Complex Urban Environments

originally presented the Interservice/Industry Training, Simulation, and Education Conference (I/ITSEC’04). The papers were rewritten in article form and reviewed for publication in JDMS in accordance with its normal review procedure for special issues. The resulting articles showcase the power of modeling and simulation in the training and education community. Even more importantly, the special issue accentuates the universality of challenges faced by modeling and simulation professionals across the defense M&S domains. The first paper, “Adapting to Urban Warfare,” by Ceranowicz and Torpey, discusses the Urban Resolve experiments being conducted by the U.S. Joint Forces Command J9 Directorate and the Joint Advanced Warfighting Program at IDA. The experiments are focused on evaluating whether future sensors will provide a significantly higher degree of situational awareness in urban operations. The authors explain how the dense environment characteristics of urban areas pose significant challenges for current combat simulations and provide a comprehensive look at the issues associated with adapting simulations for urban warfare. In the next paper, “Advanced Message Routing for Scalable Distributed Simulations,” Gottschalk, Amburn, and Davis describe the communications infrastructure used to run the large-scale entity simulations supporting the same set of Urban Resolve experiments. To achieve truly large-scale (over 1M) clutter entities, their work extends the RTI-s software route infrastructure to accommodate a more general router topology. The third paper, “The Future of Mixed Reality: Issues in Illumination and Shadows,” by Konttinen, Hughes, and Pattanaik, addresses technologies necessary to fully immerse dismounted soldiers in virtual environments. Augmented reality will provide significant enhancements in training effectiveness, practicality, and flexibility. This paper documents, in a rigorous manner, technical lessons derived from experiments and research in this area. The authors have captured many of the issues, proposed solutions, and demonstrated the efficacy of the proposed approach. Finally, in “A Validation Methodology for Human Behavior Representation Models,” Goerger, McGinnis, and Darken have taken up a challenge faced by modelers across M&S communities: validation. Further, they chose as the stage for this task the representation of human behavior itself, arguably the most difficult component of warfare to simulate. They measured performance bias on the part of the experts as it affects both the accuracy and consistency of their judgments. The M&S community has begun to consider improving the evaluation by subject matter experts by providing some common evaluation criteria. Goerger, et al, have provided measurements that suggest the type of criteria that could be used successfully. While applied to human performance, their results are applicable across a far broader area of M&S. Their work places a measurable milestone in the path to providing more robust validation for simulations. In closing, my sincerest thanks to Dr. Margaret Loper of GTRI, Dr. Sue Numrich of IDA, Dr. David Pratt of SAIC, and LTC. John “Buck” Surdu, Ph.D., of U.S. Army PEO STRI, all I/ITSEC reviewers, and all essential to the compilation and design of this special issue. Special Issue: Simulation Methodologies For Complex Urban Environments

Can Scientific History Repeat?

Kuhn (1962), Lakatos (1978) and Laudan (1977) all subscribe to a view of science which admits the existence of large scale entities differing from theories. Kuhn called these entities ‘paradigms’, Lakatos called them ‘research programs’ and Laudan calls them ‘research traditions’. These entities are distinguished from theories by their historical durability and the unique manner in which they succeed one another. The history of science may be described as a succession of eras during each of which one (or more) of these entities was dominant. During its era of dominance one of these entities may support several incompatible theories which replace one another successively but share certain common features. These features may be (part of) a common ontology, a common set of epistemological standards employed in gathering observational evidence, or common methodological or conceptual directives employed in solving new scientific problems. Although theories may change, these features (or some of these features) do not, instead they are the province of the large scale entity.