![]() ![]() The TeamBeam algorithm has been developed to provide a flexible tool to extract a wide array of meta-data from scientific articles. Furthermore, a crowdsourcing approach will work less well when applied to the long tail of articles that have few readers. This process can be boot-strapped by extracting the meta-data via tools, which are able to automatically retrieve relevant information. In the world of collaborative research networks, however, these tasks are typically crowdsourced. In the traditional ecosystem, publishers could afford to manually extract the relevant meta-data or impose this task on the authors of the articles. The quality of services provided by such systems depends on the information that can be extracted from articles. Examples of such research networks are Mendeley and CiteULike. Researchers are able to manage their collection of scientific articles and exchange and discuss papers with colleagues. In recent years social research networks have gained a lot of momentum. Keywords: Meta-data Extraction, Supervised Machine Learning, Content Analysis and Indexing, Natural Language Processing, Text Analysis TeamBeam performs well under testing and compares favourably with existing approaches. Three different data sets with varying characteristics are used to assess the quality of the extraction results. In the evaluation of the algorithm, its performance is compared against two heuristics and three existing meta-data extraction systems. A classification algorithm, which takes the sequence of the input into account, is then applied in two consecutive phases. The input of the algorithm is a set of blocks generated from the article text. The TeamBeam algorithm analyses a scientific article and extracts structured meta-data, such as the title, journal name and abstract, as well as information about the article's authors (e.g. In such settings, meta-data is rarely explicitly provided, leading to the need for automatically extracting this valuable information. Meta-data plays an important role in providing services to retrieve and organise the articles. Social research networks, such as Mendeley and CiteULike, provide services that support this task. Of documents and visualisation of several millionĭocuments.An important aspect of the work of researchers as well as librarians is to manage collections of scientific literature. ![]() (2001-2010), where I conducted and managed projects onĪutomatic text classification, text retrieval in millions Manager for Knowledge Discovery at the Know-Center Graz Worked as R&D project manager and later as division After receiving my MsC in 2004 I obtained a PhDĭegree, passed with distinction, in technical science in In 2011, I had the pleasure to visit Mendeley Ltd as a Marie Curie Research Fellow working on machine learning and information retrieval in academic knowledge bases.Īt Graz University of Technology with special focus onĬomputational Intelligence and Biomedical Computer Before, I was Scientific Director of the Know-Center Graz (since 2010) and assistant professor at the Knowledge Technology Institute of Graz University of Technology (since 2008). Since 2017 I am holding the Chair of Data Science at the University of Passau, following a Professorship for Media Computer Science since 2012 (also at University of Passau). ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |