Logo des Repositoriums

Auflistung nach Autor:in "Scherp, Ansgar"

1 - 9 von 9
  • Zeitschriftenartikel
    Interaktive Exploration und Visualisierung von semantischem Wissen mit SemaPlorerInteractive Exploration and Visualization of Semantic Knowledge with SemaPlorer
    (i-com: Vol. 8, No. 3, 2009) Scherp, Ansgar; Schenk, Simon; Saathoff, Carsten; Staab, Steffen
    SemaPlorer ist eine einfach zu bedienende Anwendung, die es Endanwendern erlaubt, einen verteilten, sehr großen Datensatz gemischter Qualität und von heterogener Semantik in Echtzeit zu explorieren und zu visualisieren. Benutzer können sich damit über eine interessante Region wie eine Stadt oder Ferienregion informieren. Die Visualisierung erfolgt mit Hilfe einer Karte, Medienansicht und verschiedenen kontextuellen Sichten auf die Daten, die es dem Benutzer erlauben, interaktiv mit den Datensätzen zu interagieren. Für SemaPlorer verwenden wir verschiedene semantische Datenquellen wie DBpedia, GeoNames, WordNet und persönliche FOAF-Dateien. Zudem ist ein großer, nach RDF konvertierter Datensatz von Flickr integriert worden. Weitere Datenquellen können sehr einfach in SemaPlorer hinzugefügt werden. Wir haben eine formative Evaluierung der SemaPlorer-Anwendung mit 20 Testpersonen durchgeführt. Die Ergebnisse dieser Evaluation werden analysiert und deren Auswirkung auf zukünftige Arbeiten skiz...
  • Zeitschriftenartikel
    LOD for Library Science: Benefits of Applying Linked Open Data in the Digital Library Setting
    (KI - Künstliche Intelligenz: Vol. 30, No. 2, 2016) Latif, Atif; Scherp, Ansgar; Tochtermann, Klaus
    Linked Open Data (LOD) has gained widespread adoption by large industries as well as non-profit organizations and governmental organizations. One of the early adopters of LOD technologies are libraries. Since the “early years”, libraries have been key use case and innovation driver for LOD and significantly contributed to the adoption of semantic technologies. The first part of this paper presents selected success stories of current activities in the Linked Data Library community. In a nutshell, these studies include (1) a conceptualization of the Linked Data Value chain, (2) a case study for consumption of Linked Data in a digital journal environment, and (3) an approach to publish metadata on the Semantic Web from an Open Access repository. These stories reveal a strong relationship between LOD in libraries and research topics addressed in traditional fields of computer science such as artificial intelligence, databases, and knowledge discovery. Thus, in the second part of this paper we systematically review the relation of LOD in digital libraries from a computer science perspective. We discuss current LOD research topics such as data integration and schema integration, distributed data management, and others. These challenges have been discussed with computer scientists at a German national database meetup as well as with librarians from ZBW—Leibniz Information Center for Economics and at international librarians meetup.
  • Konferenzbeitrag
    Personalized mobile multimedia meets location-based services
    (Informatik 2004, Informatik verbindet, Band 2, Beiträge der 34. Jahrestagung der Gesellschaft für Informatik e.V. (GI), 2004) Boll, Susanne; Krösche, Jens; Scherp, Ansgar
    When traveling and visiting new places, tourists are mobile as they wander around and follow tours through cities and landscapes. Location-based mobile systems today typically provide and deliver the the same information to all users which however does not necessarily meet the individual user's needs. In the presented approach, we aim to address the limitations of mobile devices, the unreliability of the network, and the different user's interest for the selection and the delivery of multimedia information to mobile devices. For this, a modular platform for mobile location-aware applications and a software framework for the generation of personalized multimedia content are integrated. Our sample application shows how the approach can provide a generic application support that allows the generation of mobile location-based personalized multimedia content in the domain of travel and tourism.
  • Textdokument
    Reranking-based Recommender System with Deep Learning
    (INFORMATIK 2017, 2017) Saleh, Ahmed; Mai, Florian; Nishioka, Chifumi; Scherp, Ansgar
    An enormous volume of scientific content is published every year. The amount exceeds by far what a scientist can read in her entire life. In order to address this problem, we have developed and empirically evaluated a recommender system for scientific papers based on Twitter postings. In this paper, we improve on the previous work by a reranking approach using Deep Learning. Thus, after a list of top-k recommendations is computed, we rerank the results by employing a neural network to improve the results of the existing recommender system. We present the design of the deep reranking approach and a preliminary evaluation. Our results show that in most cases, the recommendations can be improved using our Deep Learning reranking approach.
  • Zeitschriftenartikel
    The Semantic Web: Collective Intelligence on the Web
    (Informatik-Spektrum: Vol. 34, No. 5, 2011) Janik, Maciej; Scherp, Ansgar; Staab, Steffen
    The World Wide Web has turned hypertext into a success story by enabling world-wide sharing of unstructured information and informal knowledge. The Semantic Web targets the sharing of structured information and formal knowledge pursuing objectives of achieving collective intelligence on the Web. Germane to the structure of the Semantic Web is a layering and standardization of concerns. These concerns are reflected by an architecture of the Semantic Web that we present through a common use case. Semantic Web data for the use case is now found on the Web and is part of a quickly growing set of Semantic Web resources available for formal processing.
  • Konferenzbeitrag
    Web 2.0 and traditional knowledge management processes
    (WM2009: 5th conference on professional knowledge management, 2009) Scherp, Ansgar; Schwagereit, Felix; Ireson, Neil
    The paper discusses the use of Web 2.0 as a new means for knowledge management for professional organisations in general, and for emergency response in particular. It is argued that there is no clear understanding of how traditional knowledge management and Web 2.0 processes align. Thus, this paper analyses traditional knowledge management processes in the context of Web 2.0 processes and presents an alignment in a common knowledge management model. We believe that an understanding and alignment of the Web 2.0 and the traditional knowledge management processes is essential to fully realise the potential of designing and developing Web 2.0 knowledge management applications. The common model clearly shows where each Web 2.0 process can be applied, and thus the different characteristics of the Web 2.0 and organisational processes can be taken into account. Finally, we examine the application of Web 2.0-based knowledge management systems for emergency response and present the initial work on developing a tool to support knowledge management in emergency response. This tool is embedded in the context of the WeKnowIt research project that aims at examining how Web 2.0 techniques such as user generated content, question and answering and social networking can be applied in the emergency response domain.
  • Konferenzbeitrag
    What If We Encoded Words as Matrices and Used Matrix Multiplication as Composition Function?
    (INFORMATIK 2019: 50 Jahre Gesellschaft für Informatik – Informatik für Gesellschaft, 2019) Galke, Lukas; Mai, Florian; Scherp, Ansgar
    We summarize our contribution to the International Conference on Learning Representations CBOW Is Not All You Need: Combining CBOW with the Compositional Matrix Space Model, 2019.We construct a text encoder that learns matrix representations of words from unlabeled text, while using matrix multiplication as composition function. We show that our text encoder outperforms continuous bag-of-word representations on 9 out of 10 linguistic probing tasks and argue that the learned representations are complementary to the ones of vector-based approaches. Hence, we construct a hybrid model that jointly learns a matrix and a vector for each word. This hybrid model yields higher scores than purely vector-based approaches on 10 out of 16 downstream tasks in a controlled experiment with the same capacity and training data. Across all 16 tasks, the hybrid model achieves an average improvement of 1.2%. These results are insofar promising, as they open up new opportunities to efficiently incorporate order awareness into word embedding models.
  • Textdokument
    Word Embeddings for Practical Information Retrieval
    (INFORMATIK 2017, 2017) Galke, Lukas; Saleh, Ahmed; Scherp, Ansgar
    We assess the suitability of word embeddings for practical information retrieval scenarios. Thus, we assume that users issue ad-hoc short queries where we return the first twenty retrieved documents after applying a boolean matching operation between the query and the documents. We compare the performance of several techniques that leverage word embeddings in the retrieval models to compute the similarity between the query and the documents, namely word centroid similarity, paragraph vectors, Word Mover’s distance, as well as our novel inverse document frequency (IDF) re-weighted word centroid similarity. We evaluate the performance using the ranking metrics mean average precision, mean reciprocal rank, and normalized discounted cumulative gain. Additionally, we inspect the retrieval models’ sensitivity to document length by using either only the title or the full-text of the documents for the retrieval task. We conclude that word centroid similarity is the best competitor to state-of-the-art retrieval models. It can be further improved by re-weighting the word frequencies with IDF before aggregating the respective word vectors of the embedding. The proposed cosine similarity of IDF re-weighted word vectors is competitive to the TF-IDF baseline and even outperforms it in case of the news domain with a relative percentage of 15%.
  • Konferenzbeitrag
    Workshop on Data Engineering for Data Science (DE4DS)
    (BTW 2023, 2023) Schenkel, Ralf; Scherp, Ansgar
    Der Workshop „Data Engineering for Data Science“ zielt auf Aspekte des Data Engineering, die zwar zentrale Bestandteile jedes Data-Science-Projektes sind, aber in der Forschung oft zugunsten von eher mathematischen Aspekten zu kurz kommen. Typische Themen, die wir auf dem Workshop erwarten, sind z.B. Datenaufbereitung und -integration, skalierbare Verarbeitung von Data-Science-Prozessen, Datenqualität und Benchmarks (siehe auch die Themenliste im Call for Papers unten). Neben wissenschaftlichen Beiträgen sind auch eher praktisch orientierte Beiträge über Werkzeuge und Anwendungen willkommen. Je nach Anzahl der angenommenen Beiträge sind eingeladene Vorträge vorgesehen.