We present an implemented approach for domain-restricted question answering from structured knowledge sources, based on robust semantic analysis in a hybrid NLP system architecture. We perform question interpretation and answer extraction in an architecture that builds on a lexical-conceptual structure for question interpretation, which is interfaced with domain-specific concepts and properties in a structured knowledge base. Question interpretation involves a limited amount of domain-specific inferences, and accounts for higher-level quantificational questions. Question interpretation and answer extraction are modular components that interact in clearly defined ways. We derive so-called proto queries from the linguistic representations, which provide partial constraints for answer extraction from the underlying knowledge sources. The search queries we construct from proto queries effectively compute minimal spanning trees from the underlying knowledge sources. Our approach naturally extends to multilingual question answering, and has been developed as a prototype system for two application domains: the domain of Nobel prize winners, and the domain of Language Technology, on the basis of the large ontology underlying the information portal LT WORLD.
With increased computing power more data than ever are being and will be produced, stored and (re-) used. Data are collected in databases, computed and annotated, or transformed by specific tools. The knowledge from data is documented in research publications, reports, presentations, or other types of files. The management of data and knowledge is difficult, and even more complicated is their re-use, exchange, or integration. To allow for quality analysis or integration across data sets and to ensure access to scientific knowledge, additional information-Research Information-has to be assigned to data and knowledge entities. We present the metadata model CERIF to add information to entities such as Publication, Project, Organisation, Person, Product, Patent, Service, Equipment, and Facility and to manage the semantically enhanced relationships between these entities in a formalized way. CERIF has been released as an EC Recommendation to European Member States in 2000. Here, we refer to the latest version CERIF 2008-1.0.
Abstract:In the context of the wide research environment we introduce the CERIF (Common European Research Information Format) data model which (a) has a richer structure than the usual metadata standards used in research information; (b) separates base entities from link entities thus providing flexibility in expressing role based temporal relationships; (c) defines a distinct semantic layer so that relationship roles in link entities and controlled value lists in base entities are separately managed and multiple vocabularies can be used and related to each other; (d) can generate the common metadata formats used in research information. CERIF is used widely and is an EU Recommendation to Member States. At the request of the European Commission, CERIF is maintained, developed and promoted by euroCRIS.
Abstract. The OpenAIREplus project aims to further develop and operate the OpenAIRE e-infrastructure, in order to provide a central entry point to Open Access and non-Open Access publications and datasets funded by the European Commission and National agencies. The infrastructure provides the services to populate, curate, and enrich an Information Space by collecting metadata descriptions relative to organizations, data sources, projects, funding programmes, persons, publications, and datasets. Stakeholders in the research process and scientific communication, such as researchers, funding agencies, organizations involved in projects, project coordinators, can here find the information to improve their research and statistics to measure the impact of Open Access and funding schemes over research. In this paper, we introduce the functional requirements to be satisfied and describe the OpenAIREplus data model entities and relationships required to represent information capable of meeting them.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.