The Experts below are selected from a list of 10368 Experts worldwide ranked by ideXlab platform

Christoph Meinel - One of the best experts on this subject based on the ideXlab platform.

  • E-Librarian Service: User-Friendly Semantic Search in Digital Libraries
    2011
    Co-Authors: Serge Linckels, Christoph Meinel
    Abstract:

    This book introduces a new approach to designing E-Librarian Services. With the help of this system, users will be able to retrieve multimedia resources from digital libraries more efficiently than they would by browsing through an index or by using a simple keyword search. E-Librarian Services combine recent advances in multimedia information retrieval with aspects of human-machine interfaces, such as the ability to ask questions in natural language; they simulate a human Librarian by finding and delivering the most relevant documents that offer users potential answers to their queries. The premise is that more pertinent results can be retrieved if the search engine understands the meaning of the query; the returned results are therefore logical consequences of an inference rather than of keyword matches. Moreover, E-Librarian Services always provide users with a solution, even in situations where they are unable to offer a comprehensive answer.

  • e Librarian Service user friendly semantic search in digital libraries
    2011
    Co-Authors: Serge Linckels, Christoph Meinel
    Abstract:

    This book introduces a new approach to designing E-Librarian Services. With the help of this system, users will be able to retrieve multimedia resources from digital libraries more efficiently than they would by browsing through an index or by using a simple keyword search. E-Librarian Services combine recent advances in multimedia information retrieval with aspects of human-machine interfaces, such as the ability to ask questions in natural language; they simulate a human Librarian by finding and delivering the most relevant documents that offer users potential answers to their queries. The premise is that more pertinent results can be retrieved if the search engine understands the meaning of the query; the returned results are therefore logical consequences of an inference rather than of keyword matches. Moreover, E-Librarian Services always provide users with a solution, even in situations where they are unable to offer a comprehensive answer.

  • Design of the Natural Language Processing Module
    X.media.publishing, 2011
    Co-Authors: Serge Linckels, Christoph Meinel
    Abstract:

    An E-Librarian Service allows users to enter complete questions in natural language (NL) in order to improve the retrieval capabilities (see section 1.3.3). The aim of the natural language processing (NLP) module of an E-Librarian Service is to translate a user question into a logical and computer-readable form. The more precise and accurate this translation is, the more complex the algorithm gets. In this chapter we present the necessary principles to design the NLP module of an E-Librarian Service that is able to “understand” the meaning of a user question and to translate it into a logical form.

  • optimizing the retrieval of pertinent answers for nl questions with the e Librarian Service
    SMRR'07 Proceedings of the 2007 International Conference on Service Matchmaking and Resource Retrieval in the Semantic Web - Volume 243, 2007
    Co-Authors: Serge Linckels, Harald Sack, Christoph Meinel
    Abstract:

    There is a growing discrepancy between the creation of digital content and its actual employment and usefulness in a learning society. Technologies for recording lectures have become readily available and the sheer number and size of such objects produced grows exponentially. However, in practice most recordings are monolithic entities that cannot be integrated into an active learning process offhand. To overcome this problem, recorded lectures have to be semantically annotated to become full-fledged e-learning objects facilitating automated reasoning over their content. We present a running web-based system -- the e-Librarian Service CHESt -- that is able to match a user's question given in natural language to a selection of semantically pertinent learning objects based on an adapted best cover algorithm. We show with empirical data that the precision of our e-Librarian Service is much more efficient than traditional keyword-based information retrieval; it yields a correct answer in most of the cases (93% of the queries), and mostly with a high precision, i.e., without supplementary hits. We also describe some ideas to improve the retrieval performance by user feedback.

  • SMRR - Optimizing the retrieval of pertinent answers for NL questions with the E-Librarian Service
    2007
    Co-Authors: Serge Linckels, Harald Sack, Christoph Meinel
    Abstract:

    There is a growing discrepancy between the creation of digital content and its actual employment and usefulness in a learning society. Technologies for recording lectures have become readily available and the sheer number and size of such objects produced grows exponentially. However, in practice most recordings are monolithic entities that cannot be integrated into an active learning process offhand. To overcome this problem, recorded lectures have to be semantically annotated to become full-fledged e-learning objects facilitating automated reasoning over their content. We present a running web-based system -- the e-Librarian Service CHESt -- that is able to match a user's question given in natural language to a selection of semantically pertinent learning objects based on an adapted best cover algorithm. We show with empirical data that the precision of our e-Librarian Service is much more efficient than traditional keyword-based information retrieval; it yields a correct answer in most of the cases (93% of the queries), and mostly with a high precision, i.e., without supplementary hits. We also describe some ideas to improve the retrieval performance by user feedback.

Serge Linckels - One of the best experts on this subject based on the ideXlab platform.

  • E-Librarian Service: User-Friendly Semantic Search in Digital Libraries
    2011
    Co-Authors: Serge Linckels, Christoph Meinel
    Abstract:

    This book introduces a new approach to designing E-Librarian Services. With the help of this system, users will be able to retrieve multimedia resources from digital libraries more efficiently than they would by browsing through an index or by using a simple keyword search. E-Librarian Services combine recent advances in multimedia information retrieval with aspects of human-machine interfaces, such as the ability to ask questions in natural language; they simulate a human Librarian by finding and delivering the most relevant documents that offer users potential answers to their queries. The premise is that more pertinent results can be retrieved if the search engine understands the meaning of the query; the returned results are therefore logical consequences of an inference rather than of keyword matches. Moreover, E-Librarian Services always provide users with a solution, even in situations where they are unable to offer a comprehensive answer.

  • e Librarian Service user friendly semantic search in digital libraries
    2011
    Co-Authors: Serge Linckels, Christoph Meinel
    Abstract:

    This book introduces a new approach to designing E-Librarian Services. With the help of this system, users will be able to retrieve multimedia resources from digital libraries more efficiently than they would by browsing through an index or by using a simple keyword search. E-Librarian Services combine recent advances in multimedia information retrieval with aspects of human-machine interfaces, such as the ability to ask questions in natural language; they simulate a human Librarian by finding and delivering the most relevant documents that offer users potential answers to their queries. The premise is that more pertinent results can be retrieved if the search engine understands the meaning of the query; the returned results are therefore logical consequences of an inference rather than of keyword matches. Moreover, E-Librarian Services always provide users with a solution, even in situations where they are unable to offer a comprehensive answer.

  • Design of the Natural Language Processing Module
    X.media.publishing, 2011
    Co-Authors: Serge Linckels, Christoph Meinel
    Abstract:

    An E-Librarian Service allows users to enter complete questions in natural language (NL) in order to improve the retrieval capabilities (see section 1.3.3). The aim of the natural language processing (NLP) module of an E-Librarian Service is to translate a user question into a logical and computer-readable form. The more precise and accurate this translation is, the more complex the algorithm gets. In this chapter we present the necessary principles to design the NLP module of an E-Librarian Service that is able to “understand” the meaning of a user question and to translate it into a logical form.

  • optimizing the retrieval of pertinent answers for nl questions with the e Librarian Service
    SMRR'07 Proceedings of the 2007 International Conference on Service Matchmaking and Resource Retrieval in the Semantic Web - Volume 243, 2007
    Co-Authors: Serge Linckels, Harald Sack, Christoph Meinel
    Abstract:

    There is a growing discrepancy between the creation of digital content and its actual employment and usefulness in a learning society. Technologies for recording lectures have become readily available and the sheer number and size of such objects produced grows exponentially. However, in practice most recordings are monolithic entities that cannot be integrated into an active learning process offhand. To overcome this problem, recorded lectures have to be semantically annotated to become full-fledged e-learning objects facilitating automated reasoning over their content. We present a running web-based system -- the e-Librarian Service CHESt -- that is able to match a user's question given in natural language to a selection of semantically pertinent learning objects based on an adapted best cover algorithm. We show with empirical data that the precision of our e-Librarian Service is much more efficient than traditional keyword-based information retrieval; it yields a correct answer in most of the cases (93% of the queries), and mostly with a high precision, i.e., without supplementary hits. We also describe some ideas to improve the retrieval performance by user feedback.

  • SMRR - Optimizing the retrieval of pertinent answers for NL questions with the E-Librarian Service
    2007
    Co-Authors: Serge Linckels, Harald Sack, Christoph Meinel
    Abstract:

    There is a growing discrepancy between the creation of digital content and its actual employment and usefulness in a learning society. Technologies for recording lectures have become readily available and the sheer number and size of such objects produced grows exponentially. However, in practice most recordings are monolithic entities that cannot be integrated into an active learning process offhand. To overcome this problem, recorded lectures have to be semantically annotated to become full-fledged e-learning objects facilitating automated reasoning over their content. We present a running web-based system -- the e-Librarian Service CHESt -- that is able to match a user's question given in natural language to a selection of semantically pertinent learning objects based on an adapted best cover algorithm. We show with empirical data that the precision of our e-Librarian Service is much more efficient than traditional keyword-based information retrieval; it yields a correct answer in most of the cases (93% of the queries), and mostly with a high precision, i.e., without supplementary hits. We also describe some ideas to improve the retrieval performance by user feedback.

Regan Brumagen - One of the best experts on this subject based on the ideXlab platform.

Pang Nan - One of the best experts on this subject based on the ideXlab platform.

Thomas Engel - One of the best experts on this subject based on the ideXlab platform.

  • an e Librarian Service that understands natural language questions from students
    CAiSE Forum, 2006
    Co-Authors: Serge Linckels, Christoph Meinel, Thomas Engel
    Abstract:

    In this paper we present an e-Librarian Service which is able to retrieve multimedia resources from a knowledge base in a more efficient way than by browsing through an index or by using a simple keyword search. Our premise is that more pertinent results would be retrieved if the e-Librarian Service had a semantic search engine which understood the sense of the user’s query. This requires that the user must be given the means to enter semantics. We explored the approach to allow the user to formulate a complete question in natural language. The background theory was implemented in two different prototypes.

  • CAiSE Forum - An e-Librarian Service that Understands Natural Language Questions from Students.
    2006
    Co-Authors: Serge Linckels, Christoph Meinel, Thomas Engel
    Abstract:

    In this paper we present an e-Librarian Service which is able to retrieve multimedia resources from a knowledge base in a more efficient way than by browsing through an index or by using a simple keyword search. Our premise is that more pertinent results would be retrieved if the e-Librarian Service had a semantic search engine which understood the sense of the user’s query. This requires that the user must be given the means to enter semantics. We explored the approach to allow the user to formulate a complete question in natural language. The background theory was implemented in two different prototypes.