Multiple Types Of Entities Research Articles

Ontology-Based Graphs of Research Communities: A Tool for Understanding Threat Reduction Networks.

Scientific research communities can be represented as heterogeneous or multidimensional networks encompassing multiple types of entities and relationships. These networks might include researchers, institutions, meetings, and publications, connected by relationships like authorship, employment, and attendance. We describe a method for efficiently and flexibly capturing, storing, and extracting information from multidimensional scientific networks using a graph database. The database structure is based on an ontology that captures allowable types of entities and relationships. This allows us to construct a variety of projections of the underlying multidimensional graph through database queries to answer specific research questions. We demonstrate this process through a study of the U.S. Biological Threat Reduction Program (BTRP), which seeks to develop Threat Reduction Networks to build and strengthen a sustainable international community of biosecurity, biosafety, and biosurveillance experts to address shared biological threat reduction challenges. Networks like these create connectional intelligence among researchers and institutions around the world, and are central to the concept of cooperative threat reduction. Our analysis focuses on a series of seven BTRP genome sequencing training workshops, showing how they created a growing network of participants and countries over time, which is also reflected in coauthorship relationships among attendees. By capturing concept and relationship hierarchies, our ontology-based approach allows us to pose general or specific questions about networks within the same framework. This approach can be applied to other research communities or multidimensional social networks to capture, analyze, and visualize different types of interactions and how they change over time.

HEEL: exploratory entity linking for heterogeneous information networks

A heterogeneous information network (HIN) is a ubiquitous data model, consisting of multiple types of entities and relations. Names of entities in HINs are inherently ambiguous, making it difficult to fully disambiguate a HIN. In this paper, we introduce the task of exploratory entity linking for HINs. Given a partially disambiguated HIN, we aim at linking ambiguous names to disambiguated entities in the HIN if their referent entities are present. We also try to “explore” other alternatives by discovering new entities and adding them to the HIN. A partial classification EM-based approach is proposed to address this task. We present a constrained probability propagation model to link surface names to entities in the HIN. New entity detection process is modeled as a maximum edge weight clique problem. Experiments illustrate that our method outperforms state-of-the-art methods for entity linking with HINs and author name disambiguation.

A Text Mining Pipeline Using Active and Deep Learning Aimed at Curating Information in Computational Neuroscience

The curation of neuroscience entities is crucial to ongoing efforts in neuroinformatics and computational neuroscience, such as those being deployed in the context of continuing large-scale brain modelling projects. However, manually sifting through thousands of articles for new information about modelled entities is a painstaking and low-reward task. Text mining can be used to help a curator extract relevant information from this literature in a systematic way. We propose the application of text mining methods for the neuroscience literature. Specifically, two computational neuroscientists annotated a corpus of entities pertinent to neuroscience using active learning techniques to enable swift, targeted annotation. We then trained machine learning models to recognise the entities that have been identified. The entities covered are Neuron Types, Brain Regions, Experimental Values, Units, Ion Currents, Channels, and Conductances and Model organisms. We tested a traditional rule-based approach, a conditional random field and a model using deep learning named entity recognition, finding that the deep learning model was superior. Our final results show that we can detect a range of named entities of interest to the neuroscientist with a macro average precision, recall and F1 score of 0.866, 0.817 and 0.837 respectively. The contributions of this work are as follows: 1) We provide a set of Named Entity Recognition (NER) tools that are capable of detecting neuroscience entities with performance above or similar to prior work. 2) We propose a methodology for training NER tools for neuroscience that requires very little training data to get strong performance. This can be adapted for any sub-domain within neuroscience. 3) We provide a small corpus with annotations for multiple entity types, as well as annotation guidelines to help others reproduce our experiments.

Hete_MESE: Multi-Dimensional Community Detection Algorithm Based on Multiplex Network Extraction and Seed Expansion for Heterogeneous Information Networks

Most real-world information networks are heterogeneous, which contain multiple types of entities and relations between the entities. Large-scale and heterogeneity are the typical properties of heterogeneous information networks, and their community structures are often overlapping, complex, and diverse. The existing community detection algorithms without considering the above-mentioned properties may lead to low accuracy or high time complexity of community detection. In this paper, we study the multi-dimensional heterogeneous community detection problem for large-scale heterogeneous information networks with general topology structures. We define the concept of node-centric community and propose a multi-dimensional community detection algorithm referred as Hete_MESE. Specifically, we first specify one of the multiple entity types in heterogeneous information networks as community centric node type and extract the multiplex networks accordingly, and then, overlapping node-centric communities are detected based on the multiplex networks, which are considered as the seed communities to absorb the other entity types to generate the heterogeneous communities utilizing seed expansion. Taking heterogeneous academic network as an example, the effects of Hete_MESE are evaluated through extensive experiments, and the features of detected multi-dimensional academic communities are analyzed. The results demonstrate that Hete_MESE can accurately and effectively detect the meaningful overlapping and heterogeneous communities in heterogeneous information networks with general topologies from multiple dimensions. Moreover, Hete_MESE has linear time complexity, so it can be applied to large-scale heterogeneous information networks.

A General Recommendation Model for Heterogeneous Networks

Heterogeneous networks refer to the networks comprising multiple types of entities as well as their interaction relationships. They arise in a great variety of domains, for example, event-based social networks Meetup and Plancast, and DBLP. Recommendation is a useful task in these heterogeneous network systems. Although many recommendation algorithms are proposed for heterogeneous data, none of them is able to explicitly model the influence strength between different types of entities, which is useful not only for achieving higher recommendation accuracy but also better understanding the role of each entity type in recommendation problems. Moreover, many of those algorithms are designed for a particular task, and hence it is challenging to apply them in other problems. In this paper, we propose a graph-based model, called HeteRS, which can solve general recommendation problems on heterogeneous networks. Our method models the rich information with a heterogeneous graph and considers the recommendation problem as a query-dependent node proximity problem. To address the challenging issue of weighting the influences between different types of entities, we propose a learning scheme to set the influence weights between different types of entities in recommendation. Experimental results on real-world datasets demonstrate that our proposed method significantly outperforms the baseline methods in our experiments for all the recommendation tasks, and the learned influence weights help understanding user behaviors.

PKDE4J: Entity and relation extraction for public knowledge discovery

Due to an enormous number of scientific publications that cannot be handled manually, there is a rising interest in text-mining techniques for automated information extraction, especially in the biomedical field. Such techniques provide effective means of information search, knowledge discovery, and hypothesis generation. Most previous studies have primarily focused on the design and performance improvement of either named entity recognition or relation extraction. In this paper, we present PKDE4J, a comprehensive text-mining system that integrates dictionary-based entity extraction and rule-based relation extraction in a highly flexible and extensible framework. Starting with the Stanford CoreNLP, we developed the system to cope with multiple types of entities and relations. The system also has fairly good performance in terms of accuracy as well as the ability to configure text-processing components. We demonstrate its competitive performance by evaluating it on many corpora and found that it surpasses existing systems with average F-measures of 85% for entity extraction and 81% for relation extraction.

Scaling with Confidence

Constraints ubiquitously exist in many real-life applications for entity resolution. However, it is always challenging to effectively specify and use such constraints for performing ER tasks. In particular, not every constraint is equally robust. Adding weights to express the “confidence” on constraints thus becomes a natural choice. In this paper, the authors study entity resolution (ER), the problem of determining which records in one or more databases refer to the same entities, in the presence of weighted constraints. They propose a unified framework that allows us to associate a weight for each constraint, capturing the confidence for its robustness in an ER model. The authors develop an approach to learn weighted constraints based on domain knowledge, and investigate how effectively and efficiently weighted constraints can be used for generating an ER clustering and for determining a propagation order across multiple entity types. Their experimental study shows that using weighted constraints can lead to improved ER quality and scalability.

Restricted random labeling: testing for between-group interaction after controlling for joint population and within-group spatial structure

Statistical measures of spatial interaction between multiple types of entities are commonly assessed against a null model of either toroidal shift (TS), which controls for spatial structure of individual subpopulations, or random labeling (RL), which controls for spatial structure of the joint population. Neither null model controls for both types of spatial structure simultaneously, although this may sometimes be desirable when more than two subpopulations are present. To address this, we propose a flexible framework for specifying null models that we refer to as restricted random labeling (rRL). Under rRL, a specified subset of individuals is restricted and other individuals are randomly relabeled. Within this framework, two specific null models are proposed for pairwise analysis within populations consisting of three or more subpopulations, to simultaneously control for spatial structure in the joint population and one or the other of the two subpopulations being analyzed. Formulas are presented for calculating expected nearest neighbor counts and co-location quotients within the proposed framework. Differences between TS, RL and rRL are illustrated by application to six types of generating processes in a simulation study, and to empirical datasets of tree species in a forest and crime locations in an urban setting. These examples show that rRL null models are typically stricter than either TS or RL, which often detect “interactions” that are an expected consequence either of the joint population pattern or of individual subpopulation patterns.

Constructing topical hierarchies in heterogeneous information networks

Many digital documentary data collections (e.g., scientific publications, enterprise reports, news articles, and social media) can be modeled as a heterogeneous information network, linking text with multiple types of entities. Constructing high-quality hierarchies that can represent topics at multiple granularities benefits tasks such as search, information browsing, and pattern mining. In this work, we present an algorithm for recursively constructing multi-typed topical hierarchies. Contrary to traditional text-based topic modeling, our approach handles both textual phrases and multiple types of entities by a newly designed clustering and ranking algorithm for heterogeneous network data, as well as mining and ranking topical patterns of different types. Our experiments on datasets from two different domains demonstrate that our algorithm yields high-quality, multi-typed topical hierarchies.

Network Entity Relationship Diagrams

Data sets which contain multiple entity types and the relationships which exist between them are promising sources for multi-mode analysis in Network Science. This paper proposes a visualization technique to be used as a planning tool and to standardize the exchange between researchers of the multi-mode analysis potential of any data set.

The relational database model and multiple multicenter clinical trials

The Southwest Oncology Group (SWOG) chose to use a relational database management system (RDBMS) for the management of data from multiple clinical trials because of the underlying relational model's inherent flexibility and the natural way multiple entity types (patients, studies, and participants) can be accomodated. The tradeoffs to using the relational model as compared to using the hierarchical model include added computing cycles due to deferred data linkages and added procedural complexity due to the necessity of implementing protections against referential integrity violations. The SWOG uses its RDBMS as a platform on which to build data operations software. This data operations software, which is written in a compiled computer language, allows multiple users to simultaneously update the database and is interactive with respect to the detection of conditions requiring action and the presentation of options for dealing with those conditions. The relational model facilitates the development and maintenance of data operations software.