Search (7 results, page 1 of 1)

0.0012504549 = product of:
  0.028760463 = sum of:
    0.028760463 = sum of:
      0.0094278185 = weight(_text_:1 in 4645) [ClassicSimilarity], result of:
        0.0094278185 = score(doc=4645,freq=2.0), product of:
          0.057894554 = queryWeight, product of:
            2.4565027 = idf(docFreq=10304, maxDocs=44218)
            0.023567878 = queryNorm
          0.16284466 = fieldWeight in 4645, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            2.4565027 = idf(docFreq=10304, maxDocs=44218)
            0.046875 = fieldNorm(doc=4645)
      0.019332644 = weight(_text_:29 in 4645) [ClassicSimilarity], result of:
        0.019332644 = score(doc=4645,freq=2.0), product of:
          0.08290443 = queryWeight, product of:
            3.5176873 = idf(docFreq=3565, maxDocs=44218)
            0.023567878 = queryNorm
          0.23319192 = fieldWeight in 4645, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            3.5176873 = idf(docFreq=3565, maxDocs=44218)
            0.046875 = fieldNorm(doc=4645)
  0.04347826 = coord(1/23)

Abstract

Evaluation of ontology alignments is in practice done in two ways: (1) assessing individual correspondences and (2) comparing the alignment to a reference alignment. However, this type of evaluation does not guarantee that an application which uses the alignment will perform well. In this paper, we contribute to the current ontology alignment evaluation practices by proposing two alternative evaluation methods that take into account some characteristics of a usage scenario without doing a full-fledged end-to-end evaluation. We compare different evaluation approaches in three case studies, focussing on methodological issues. Each case study considers an alignment between a different pair of ontologies, ranging from rich and well-structured to small and poorly structured. This enables us to conclude on the use of different evaluation approaches in different settings.

Date

29. 7.2011 14:44:56

8.551002E-4 = product of:
  0.0098336525 = sum of:
    0.00476276 = product of:
      0.00952552 = sum of:
        0.00952552 = weight(_text_:1 in 553) [ClassicSimilarity], result of:
          0.00952552 = score(doc=553,freq=6.0), product of:
            0.057894554 = queryWeight, product of:
              2.4565027 = idf(docFreq=10304, maxDocs=44218)
              0.023567878 = queryNorm
            0.16453223 = fieldWeight in 553, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              2.4565027 = idf(docFreq=10304, maxDocs=44218)
              0.02734375 = fieldNorm(doc=553)
      0.5 = coord(1/2)
    0.005070892 = product of:
      0.010141784 = sum of:
        0.010141784 = weight(_text_:international in 553) [ClassicSimilarity], result of:
          0.010141784 = score(doc=553,freq=2.0), product of:
            0.078619614 = queryWeight, product of:
              3.33588 = idf(docFreq=4276, maxDocs=44218)
              0.023567878 = queryNorm
            0.12899815 = fieldWeight in 553, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.33588 = idf(docFreq=4276, maxDocs=44218)
              0.02734375 = fieldNorm(doc=553)
      0.5 = coord(1/2)
  0.08695652 = coord(2/23)

Abstract

Currently, a number of efforts are being carried out to integrate collections from different institutions and containing heterogeneous material. Examples of such projects are The European Library [1] and the Memory of the Netherlands [2]. A crucial point for the success of these is the availability to provide a unified access on top of the different collections, e.g. using one single vocabulary for querying or browsing the objects they contain. This is made difficult by the fact that the objects from different collections are often described using different vocabularies - thesauri, classification schemes - and are therefore not interoperable at the semantic level. To solve this problem, one can turn to semantic links - mappings - between the elements of the different vocabularies. If one knows that a concept C from a vocabulary V is semantically equivalent to a concept to a concept D from vocabulary W, then an appropriate search engine can return all the objects that were indexed against D for a query for objects described using C. We thus have an access to other collections, using a single one vocabulary. This is however an ideal situation, and hard alignment work is required to reach it. Several projects in the past have tried to implement such a solution, like MACS [3] and Renardus [4]. They have demonstrated very interesting results, but also highlighted the difficulty of aligning manually all the different vocabularies involved in practical cases, which sometimes contain hundreds of thousands of concepts. To alleviate this problem, a number of tools have been proposed in order to provide with candidate mappings between two input vocabularies, making alignment a (semi-) automatic task. Recently, the Semantic Web community has produced a lot of these alignment tools'. Several techniques are found, depending on the material they exploit: labels of concepts, structure of vocabularies, collection objects and external knowledge sources. Throughout our presentation, we will present a concrete heterogeneity case where alignment techniques have been applied to build a (pilot) browser, developed in the context of the STITCH project [5]. This browser enables a unified access to two collections of illuminated manuscripts, using the description vocabulary used in the first collection, Mandragore [6], or the one used by the second, Iconclass [7]. In our talk, we will also make the point for using unified representations the vocabulary semantic and lexical information. Additionally to ease the use of the alignment tools that have these vocabularies as input, turning to a standard representation format helps designing applications that are more generic, like the browser we demonstrate. We give pointers to SKOS [8], an open and web-enabled format currently developed by the Semantic Web community.
References [1] http:// www.theeuropeanlibrary.org [2] http://www.geheugenvannederland.nl [3] http://macs.cenl.org [4] Day, M., Koch, T., Neuroth, H.: Searching and browsing multiple subject gateways in the Renardus service. In Proceedings of the RC33 Sixth International Conference on Social Science Methodology, Amsterdam , 2005. [5] http://stitch.cs.vu.nl [6] http://mandragore.bnf.fr [7] http://www.iconclass.nl [8] www.w3.org/2004/02/skos/ 1 The Semantic Web vision supposes sharing data using different conceptualizations (ontologies), and therefore implies to tackle the semantic interoperability problem

4.2027488E-4 = product of:
  0.009666322 = sum of:
    0.009666322 = product of:
      0.019332644 = sum of:
        0.019332644 = weight(_text_:29 in 39) [ClassicSimilarity], result of:
          0.019332644 = score(doc=39,freq=2.0), product of:
            0.08290443 = queryWeight, product of:
              3.5176873 = idf(docFreq=3565, maxDocs=44218)
              0.023567878 = queryNorm
            0.23319192 = fieldWeight in 39, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5176873 = idf(docFreq=3565, maxDocs=44218)
              0.046875 = fieldNorm(doc=39)
      0.5 = coord(1/2)
  0.04347826 = coord(1/23)

Date

17.11.2020 11:29:00

3.779547E-4 = product of:
  0.008692958 = sum of:
    0.008692958 = product of:
      0.017385917 = sum of:
        0.017385917 = weight(_text_:international in 3035) [ClassicSimilarity], result of:
          0.017385917 = score(doc=3035,freq=2.0), product of:
            0.078619614 = queryWeight, product of:
              3.33588 = idf(docFreq=4276, maxDocs=44218)
              0.023567878 = queryNorm
            0.22113968 = fieldWeight in 3035, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.33588 = idf(docFreq=4276, maxDocs=44218)
              0.046875 = fieldNorm(doc=3035)
      0.5 = coord(1/2)
  0.04347826 = coord(1/23)

Abstract

Most libraries and other cultural heritage institutions use controlled knowledge organisation systems, such as thesauri, to describe their collections. Unfortunately, as most of these institutions use different such systems, united access to heterogeneous collections is difficult. Things are even worse in an international context when concepts have labels in different languages. In order to overcome the multilingual interoperability problem between European Libraries, extensive work has been done to manually map concepts from different knowledge organisation systems, which is a tedious and expensive process. Within the TELplus project, we developed and evaluated methods to automatically discover these mappings, using different ontology matching techniques. In experiments on major French, English and German subject heading lists Rameau, LCSH and SWD, we show that we can automatically produce mappings of surprisingly good quality, even when using relatively naive translation and matching methods.

3.779547E-4 = product of:
  0.008692958 = sum of:
    0.008692958 = product of:
      0.017385917 = sum of:
        0.017385917 = weight(_text_:international in 3107) [ClassicSimilarity], result of:
          0.017385917 = score(doc=3107,freq=2.0), product of:
            0.078619614 = queryWeight, product of:
              3.33588 = idf(docFreq=4276, maxDocs=44218)
              0.023567878 = queryNorm
            0.22113968 = fieldWeight in 3107, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.33588 = idf(docFreq=4276, maxDocs=44218)
              0.046875 = fieldNorm(doc=3107)
      0.5 = coord(1/2)
  0.04347826 = coord(1/23)

Source

Proceedings of the 15th European Networked Knowledge Organization Systems Workshop (NKOS 2016) co-located with the 20th International Conference on Theory and Practice of Digital Libraries 2016 (TPDL 2016), Hannover, Germany, September 9, 2016. Edi. by Philipp Mayr et al. [http://ceur-ws.org/Vol-1676/=urn:nbn:de:0074-1676-5]

2.5196982E-4 = product of:
  0.0057953056 = sum of:
    0.0057953056 = product of:
      0.011590611 = sum of:
        0.011590611 = weight(_text_:international in 3398) [ClassicSimilarity], result of:
          0.011590611 = score(doc=3398,freq=2.0), product of:
            0.078619614 = queryWeight, product of:
              3.33588 = idf(docFreq=4276, maxDocs=44218)
              0.023567878 = queryNorm
            0.14742646 = fieldWeight in 3398, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.33588 = idf(docFreq=4276, maxDocs=44218)
              0.03125 = fieldNorm(doc=3398)
      0.5 = coord(1/2)
  0.04347826 = coord(1/23)

Content

This paper is based on a talk given at "Information Access for the Global Community, An International Seminar on the Universal Decimal Classification" held on 4-5 June 2007 in The Hague, The Netherlands. An abstract of this talk will be published in Extensions and Corrections to the UDC, an annual publication of the UDC consortium. Beitrag eines Themenheftes "Digital libraries and the semantic web: context, applications and research".

1.707938E-4 = product of:
  0.0039282576 = sum of:
    0.0039282576 = product of:
      0.007856515 = sum of:
        0.007856515 = weight(_text_:1 in 125) [ClassicSimilarity], result of:
          0.007856515 = score(doc=125,freq=2.0), product of:
            0.057894554 = queryWeight, product of:
              2.4565027 = idf(docFreq=10304, maxDocs=44218)
              0.023567878 = queryNorm
            0.13570388 = fieldWeight in 125, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              2.4565027 = idf(docFreq=10304, maxDocs=44218)
              0.0390625 = fieldNorm(doc=125)
      0.5 = coord(1/2)
  0.04347826 = coord(1/23)

Source

Semantic Web journal. 3(2012) no.1, S.45-64