CERMINE is a comprehensive open-source system for extracting structured metadata from scientific articles in a born-digital form. The system is based on a modular workflow, whose loosely coupled architecture allows for individual component evaluation and adjustment, enables effortless improvements and replacements of independent parts of the algorithm and facilitates future architecture expanding. The implementations of most steps are based on supervised and unsupervised machine learning techniques, which simplifies the procedure of adapting the system to new document layouts and styles. The evaluation of the extraction workflow carried out with the use of a large dataset showed good performance for most metadata types, with the average F score of 77.5 %. CERMINE system is available under an open-source licence and can be accessed at http:// cermine.ceon.pl. In this paper, we outline the overall workflow architecture and provide details about individual steps implementations. We also thoroughly compare CERMINE to similar solutions, describe evaluation methodology and finally report its results. B Dominika Tkaczyk

Directory of open access repositories:http://www.opendoar.org Registry of open access repositories: http://roar.eprints.orgRegistry of open access repository material archiving policies:

No abstract

We present a comprehensive system for extracting metadata from scholarly articles. In our approach the entire document is inspected, including headers and footers of all the pages as well as bibliographic references. The system is based on a modular workflow which allows for evaluation, unit testing and replacement of individual components. The workflow is optimized towards processing of born-digital documents, but may accept scanned document images as well. The machinelearning approaches we have chosen for solving individual tasks increase the ability to adapt to new document layouts and formats. The evaluation tests we have performed showed good results of the individual implementations and the entire metadata extraction process.

No abstract

Such information may be program funding (projects), associated datasets, related publications, citations, institutional affiliation, and also a different range of metrics indicating the scientific impact. To best exploit this range of research objects, they can manifest themselves in "enhanced publications." OpenAIRE 1 -the European Union initiative for an Open Access Infrastructure for Research in Europe-supports this enhanced form of open scholarly communication and provides access to the research output of European funded projects and open access content from a network of institutional and disciplinary repositories. Based on a series of European projects (DRIVER and DRIVER-II), Europe has built an extensive network of institutional repositories that follow a common path for interoperability via the publication and consistent use of guidelines. In its current status, OpenAIRE has aggregated more than eight million bibliographic records from over 400 providers of publications which are complemented by research data and research information, where and when the information is available.OpenAIRE moves beyond the traditional publications aggregator by interconnecting entities related to scholarly communication (currently limited to publications, research data, people, organizations, and their data sources) allowing users to navigate alongside a rich information space graph (Figure 1). It provides individual and aggregated statistics based on different facets, attributes, and linkages of the above entities. As of December 2010, OpenAIRE has been a key service of the EC's Seventh Framework Programme, at present extending to cover other funders and eventually all the European Research Area. As such, OpenAIRE users, i.e., researchers, funding organizations, and third-party services consuming information, expect to find consistent and qualitative metadata. This places data curation as a high priority, employing a series of activities both on the technical Scholarly communication is currently at a new phase where researchers' published results are more optimally shared, discovered, validated, and reused when they are exposed in their full context. This means that they are best accompanied by all the relative information that provides an insight and capacity to translate the research process and activities that have taken place. and networking levels. Data curation in OpenAIRE differs from similar activities in a data archive as it is mainly applied on the metadata level, needing to comprise heterogeneous data sources and is backed by complex organizational and technical support structures. It can also comprise of a range of actions and workflows, as will be demonstrated below. Data Curation in the OpenAIREOpenAIRE, as the pan-European infrastructure of all scientific results, faces two major challenges: diversity of scientific data and diversity of cultural approaches for good practices that span many national borders. To understand how expert research communities facilitate data curation mechanisms and carry out linking...

No abstract

Author name disambiguation allows to distinguish between two or more authors sharing the same name. In a previous paper, we have proposed a name disambiguation framework in which for each author name in each article we build a context consisting of classification codes, bibliographic references, co-authors, etc. Then, by pairwise comparison of contexts, we have been grouping contributions likely referring to the same people. In this paper we examine which elements of the context are most effective in author name disambiguation. We employ linear Support Vector Machines (SVM) to find the most influential features.