Now showing 1 - 10 of 49
  • Publication
    Can proactive behavior turn chatterbots into conversational agents?
    ( 2005)
    L'Abbate, M.
    ;
    Thiel, U.
    ;
    Kamps, T.
  • Publication
    Statistical relationship determination in automatic thesaurus construction
    ( 2005)
    Chen, L.
    ;
    Fankhauser, P.
    ;
    Thiel, U.
    ;
    Kamps, T.
  • Publication
    Supporting information access in next generation digital library architectures
    ( 2005)
    Frommholz, I.
    ;
    Knezevic, P.
    ;
    Mehta, B.
    ;
    Niederée, C.
    ;
    Risse, T.
    ;
    Thiel, U.
    Current developments on Service-oriented Architectures, Peer-to-Peer and Grid computing promise more open and flexible architectures for digital libraries. They will open the Digital Library (DL) technology to a wider clientele, allow faster adaptability and enable the usage of federative models on content and service provision. These technologies raise new challenges for the realization of DL functionalities, which are rooted in the increased heterogeneity of content, services and metadata, in the higher degree of distribution and dynamics, as well as in the omission of a central control instance. This paper discusses these opportunities and challenges for three central types of DL functionality revolving around information access: metadata management, retrieval functionality, and personalization services.
  • Publication
    Agent-based assistance in a digital library user interface
    ( 2005)
    Thiel, U.
    ;
    Brocks, H.
    ;
    Stein, A.
  • Publication
    Language modeling for effective construction of domain specific thesauri
    ( 2004)
    Chen, L.B.
    ;
    Thiel, U.
    In this paper we present an approach for effective construction of domain specific thesauri. We assume that the collection is partitioned into document categories. By taking advantage of these pre-defined categories, we are able to conceptualize a new topical language model to weight term topicality more accurately. With the help of information theory, interesting relationships among thesaurus elements are discovered deductively. Based on the "Layer-Seeds" clustering algorithm, topical terms from documents in a certain category will be organized according to their relationships in a tree-like hierarchical structure --- a thesaurus. Experimental results show that the thesaurus contains satisfactory structures, although it differs to some extent from a manually created thesaurus. A first evaluation of the thesaurus in a query expansion task yields evidence that an increase of recall can be achieved without loss of precision.
  • Publication
    Supporting information access in next generation digital library architectures
    ( 2004)
    Frommholz, I.
    ;
    Knezevic, P.
    ;
    Mehta, B.
    ;
    Niederée, C.
    ;
    Risse, W.
    ;
    Thiel, U.
  • Publication
  • Publication
    Content engineering for conversational advisory systems
    ( 2004)
    L'Abbate, M.
    ;
    Thiel, U.
    ;
    Kamps, T.
  • Publication
    Using case based retrieval techniques for handling anomalous situations in advisory dialogues
    ( 2004)
    L'Abbate, M.
    ;
    Frommholz, I.
    ;
    Thiel, U.
    ;
    Neuhold, E.
    The efficacy of expert systems often depends on the accuracy and completeness of the problem specification negotiated with the user. Therefore, efficient user interfaces are needed, in order to assist the user in identifying and supplying the required data. Our approach presented in this paper is based on the utilisation of conversational interfaces, giving users the possibility of interacting with the system by means of natural language. Through the use of flexible dialogue management plans and an advanced problem solving strategy based on case based reasoning and information retrieval, efficient user guidance during the interaction with an expert system can be achieved. Thus, the user can interactively develop a comprehensive and coherent specification of his problem, based on clarifications, explanations, and context-based factual information provided by the system. As an application framework we introduce the EU-funded Project VIP-Advisor whose objective is the development of a virtual insurance and finance assistant capable of natural language interaction.