The REDCap consortium: Building an international community of software platform partners.

Despite progress in perceptual tasks such as image classification, computers still perform poorly on cognitive tasks such as image description and question answering. Cognition is core to tasks that involve not just recognizing, but reasoning about our visual world. However, models used to tackle the rich content in images for cognitive tasks are still being trained using the same datasets designed for perceptual tasks. To achieve success at cognitive tasks, models need to understand the interactions and relationships between objects in an image. When asked "What vehicle is the person riding?", computers will need to identify the objects in an image as well as the relationships riding(man, carriage) and pulling(horse, carriage) to answer correctly that "the person is riding a horse-drawn carriage." In this paper, we present the Visual Genome dataset to enable the modeling of such relationships. We collect dense annotations of objects, attributes, and relationships within each image to learn these models. Specifically, our dataset contains over 108K images where each image has an average of $$35$$35 objects, $$26$$26 attributes, and $$21$$21 pairwise relationships between objects. We canonicalize the objects, attributes, relationships, and noun phrases in region descriptions and questions answer pairs to WordNet synsets. Together, these annotations represent the densest and largest dataset of image descriptions, objects, attributes, relationships, and question answer pairs.

/pdf/visual-genome-connecting-language-and-vision-using-15ih2ylk6r.pdf

Visual Genome: Connecting Language and Vision Using Crowdsourced Dense Image Annotations

We present YAGO, a light-weight and extensible ontology with high coverage and quality. YAGO builds on entities and relations and currently contains more than 1 million entities and 5 million facts. This includes the Is-A hierarchy as well as non-taxonomic relations between entities (such as HASONEPRIZE). The facts have been automatically extracted from Wikipedia and unified with WordNet, using a carefully designed combination of rule-based and heuristic methods described in this paper. The resulting knowledge base is a major step beyond WordNet: in quality by adding knowledge about individuals like persons, organizations, products, etc. with their semantic relationships - and in quantity by increasing the number of facts by more than an order of magnitude. Our empirical evaluation of fact correctness shows an accuracy of about 95%. YAGO is based on a logically clean model, which is decidable, extensible, and compatible with RDFS. Finally, we show how YAGO can be further extended by state-of-the-art information extraction techniques.

/pdf/yago-a-core-of-semantic-knowledge-13k3nmj6l2.pdf

Yago: a core of semantic knowledge

This paper gives an overview of the development of the field of Knowledge Engineering over the last 15 years. We discuss the paradigm shift from a transfer view to a modeling view and describe two approaches which considerably shaped research in Knowledge Engineering: Role-limiting Methods and Generic Tasks. To illustrate various concepts and methods which evolved in recent years we describe three modeling frameworks: CommonKADS, MIKE and PROTEGE-II. This description is supplemented by discussing some important methodological developments in more detail: specification languages for knowledge-based systems, problem-solving methods and ontologies. We conclude by outlining the relationship of Knowledge Engineering to Software Engineering, Information Integration and Knowledge Management.

/pdf/knowledge-engineering-principles-and-methods-6do1hbj75r.pdf

Knowledge engineering: principles and methods

The National Human Genome Research Institute (NHGRI) Catalog of Published Genome-Wide Association Studies (GWAS) Catalog provides a publicly available manually curated collection of published GWAS assaying at least 100000 singlenucleotide polymorphisms (SNPs) and all SNP-trait associations with P <110 5 . The Catalog includes 1751 curated publications of 11912 SNPs. In addition to the SNP-trait association data, the Catalog also publishes a quarterly diagram of all SNP-trait associations mapped to the SNPs’ chromosomal locations. The Catalog can be accessed via a tabular web interface, via a dynamic visualization on the human karyotype, as a downloadable tab-delimited file and as an OWL knowledge base. This article presents a number of recent improvements to the Catalog, including novel ways for users to interact with the Catalog and changes to the curation infrastructure.

/pdf/the-nhgri-gwas-catalog-a-curated-resource-of-snp-trait-3zt2r8ota7.pdf

The NHGRI GWAS Catalog, a curated resource of SNP-trait associations

Mark A. Musen, Ray W. Fergerson, William E. Grosso, Natalya F. Noy, Monica Crubezy, and John H. GennariStanford Medical InformaticsStanford UniversityStanford, California 94305-5479U.S.A.Musen@Stanford.EDUhttp://www.smi.stanford.edu/projects/protegeDuring the past decade, there has been increasingconsensus within the knowledge-based–systemscommunity on appropriate conceptual componentsfor building intelligent computer programs. Intelli-gent systems are now generally construed in termsof both domain ontologies and abstract problem-solving methods that operate on knowledge basesdefined in terms of those ontologies. There hasbeen less consensus, however, regarding how tooptimize the operational components and the userinterfaces of tools that assist developers in the con-struction of knowledge-based systems. For the mostpart, such lack of consensus is to be expected, giventhe way in which domain considerations oftendominate the way in which knowledge can best beentered, browsed, and updated in any computer-based tool. In our research group at Stanford Uni-versity, we acknowledge both the central importanceand the great variability of domain-specific idiomsthat can enhance the functionality of knowledge-acquisition tools. Our work seeks specific ways toharness this variability and to allow developers totake advantage of alternative approaches.Our latest development in a series of computer-based knowledge-acquisition systems is known asProtege-2000. Protege-2000 is a meta-tool” that“helps users to construct domain-specific knowledge-acquisition systems that application experts can useto enter and browse the content knowledge of elec-tronic knowledge bases. The architecture of Pro-tege-2000 assumes that, as with Web browsers,users will want to enhance andcustom tailor the system’s behavior by means of a variety of “plug-ins.” These plug-ins are modular pieces of programcode that add new functionalities to Protege-2000 inwell circumscribed ways. Developers can contrib-ute new Protege-2000 plug-ins to a library main-tained on the Internet, and can freely download newplug-ins to augment the behavior of their ownknowledge-acquisition systems constructed usingProtege-2000. Our approach establishes a new kindof knowledge-acquisition enterprise—one of build-ing knowledge-acquisition–tool

Component-Based Support for Building Knowledge-Acquisition Systems

In this paper, we present Web-Protege—a web-based lightweight ontology editor. Web-Protege is open source, uses the Google Web Toolkit (GWT) for the user interface, and Protege for supporting ontology services. We used components of Collaborative Protege to augment the ontology-editing environment with facilities for discussions and annotations. In this paper, we describe both the server and the client components of the system. We built the user interface using the portal metaphor, which allows easy customization of the user interface for individual users. The plug-in architecture allows easy extension of the user interface with custom components. The server component is implemented in Java and provides methods for accessing the ontology content and manages the changes the users make in different clients. A demo version is available at http://bmir-protege-dev1.stanford.edu/webprotege/.

/pdf/web-protege-a-lightweight-owl-ontology-editor-for-the-web-53f52fgry7.pdf

Web-Protege: A Lightweight OWL Ontology Editor for the Web.

The development of standard terminologies such as RadLex is becoming important in radiology applications, such as structured reporting, teaching file authoring, report indexing, and text mining. The development and maintenance of these terminologies are challenging, however, because there are few specialized tools to help developers to browse, visualize, and edit large taxonomies. Protege (http://protege.stanford.edu) is an open-source tool that allows developers to create and to manage terminologies and ontologies. It is more than a terminology-editing tool, as it also provides a platform for developers to use the terminologies in end-user applications. There are more than 70,000 registered users of Protege who are using the system to manage terminologies and ontologies in many different domains. The RadLex project has recently adopted Protege for managing its radiology terminology. Protege provides several features particularly useful to managing radiology terminologies: an intuitive graphical user interface for navigating large taxonomies, visualization components for viewing complex term relationships, and a programming interface so developers can create terminology-driven radiology applications. In addition, Protege has an extensible plug-in architecture, and its large user community has contributed a rich library of components and extensions that provide much additional useful functionalities. In this report, we describe Protege’s features and its particular advantages in the radiology domain in the creation, maintenance, and use of radiology terminology.

/pdf/protege-a-tool-for-managing-and-using-terminology-in-2dki1cml3z.pdf

Protégé: a tool for managing and using terminology in radiology applications.

The state of art in ontology design

One of the main threads in the history of knowledge-representation formalisms is the trade-off between the expressiveness of first-order logic on the one hand and the tractability and ease-of-use of frame-based systems on the other hand. Frame-based systems provide intuitive, cognitively easy-to-understand, and scalable means for modeling a domain. However, when a domain model is particularly complex, frame-based representation may lead to complicated and sometimes awkward solutions. We have encountered such problems when developing the Digital Anatomist Foundational Model, an ontology aimed at representing comprehensively the physical organization of the human body. We show that traditional frame-based techniques such as is-a hierarchies, slots (roles) and role restrictions are not sufficient for a comprehensive model of this domain. The diverse modeling challenges and problems in this project required us to use such knowledge-representation techniques as reified relations, metaclasses and a metaclass hierarchy, different propagation patterns for template and own slots, and so on. We posit that even though the modeling structure imposed by frame-based systems may sometimes lead to complicated solutions, it is still worthwhile to use frame-based representation for very large-scale projects such as this one.

Natalya F. Noy

Papers

Component-Based Support for Building Knowledge-Acquisition Systems

Web-Protege: A Lightweight OWL Ontology Editor for the Web.

Protégé: a tool for managing and using terminology in radiology applications.

The state of art in ontology design

Pushing the envelope: challenges in a frame-based representation of human anatomy