Search (17 results, page 1 of 1)

0.09524199 = product of:
  0.14286299 = sum of:
    0.08966068 = weight(_text_:systematic in 3311) [ClassicSimilarity], result of:
      0.08966068 = score(doc=3311,freq=2.0), product of:
        0.28397155 = queryWeight, product of:
          5.715473 = idf(docFreq=395, maxDocs=44218)
          0.049684696 = queryNorm
        0.31573826 = fieldWeight in 3311, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          5.715473 = idf(docFreq=395, maxDocs=44218)
          0.0390625 = fieldNorm(doc=3311)
    0.053202312 = product of:
      0.106404625 = sum of:
        0.106404625 = weight(_text_:indexing in 3311) [ClassicSimilarity], result of:
          0.106404625 = score(doc=3311,freq=14.0), product of:
            0.19018644 = queryWeight, product of:
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.049684696 = queryNorm
            0.55947536 = fieldWeight in 3311, product of:
              3.7416575 = tf(freq=14.0), with freq of:
                14.0 = termFreq=14.0
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.0390625 = fieldNorm(doc=3311)
      0.5 = coord(1/2)
  0.6666667 = coord(2/3)

Abstract

Tools for automatic subject assignment help deal with scale and sustainability in creating and enriching metadata, establishing more connections across and between resources and enhancing consistency. Although some software vendors and experimental researchers claim the tools can replace manual subject indexing, hard scientific evidence of their performance in operating information environments is scarce. A major reason for this is that research is usually conducted in laboratory conditions, excluding the complexities of real-life systems and situations. The article reviews and discusses issues with existing evaluation approaches such as problems of aboutness and relevance assessments, implying the need to use more than a single "gold standard" method when evaluating indexing and retrieval, and proposes a comprehensive evaluation framework. The framework is informed by a systematic review of the literature on evaluation approaches: evaluating indexing quality directly through assessment by an evaluator or through comparison with a gold standard, evaluating the quality of computer-assisted indexing directly in the context of an indexing workflow, and evaluating indexing quality indirectly through analyzing retrieval performance.

0.014988055 = product of:
  0.044964164 = sum of:
    0.044964164 = product of:
      0.08992833 = sum of:
        0.08992833 = weight(_text_:indexing in 4171) [ClassicSimilarity], result of:
          0.08992833 = score(doc=4171,freq=10.0), product of:
            0.19018644 = queryWeight, product of:
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.049684696 = queryNorm
            0.47284302 = fieldWeight in 4171, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.0390625 = fieldNorm(doc=4171)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

Purpose - Traditional subject indexing and classification are considered infeasible in many digital collections. This paper seeks to investigate ways of enhancing social tagging via knowledge organization systems, with a view to improving the quality of tags for increased information discovery and retrieval performance. Design/methodology/approach - Enhanced tagging interfaces were developed for exemplar online repositories, and trials were undertaken with author and reader groups to evaluate the effectiveness of tagging augmented with control vocabulary for subject indexing of papers in online repositories. Findings - The results showed that using a knowledge organisation system to augment tagging does appear to increase the effectiveness of non-specialist users (that is, without information science training) in subject indexing. Research limitations/implications - While limited by the size and scope of the trials undertaken, these results do point to the usefulness of a mixed approach in supporting the subject indexing of online resources. Originality/value - The value of this work is as a guide to future developments in the practical support for resource indexing in online repositories.

0.0134631805 = product of:
  0.04038954 = sum of:
    0.04038954 = product of:
      0.08077908 = sum of:
        0.08077908 = weight(_text_:22 in 100) [ClassicSimilarity], result of:
          0.08077908 = score(doc=100,freq=2.0), product of:
            0.17398734 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.049684696 = queryNorm
            0.46428138 = fieldWeight in 100, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.09375 = fieldNorm(doc=100)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Date

22. 9.2007 15:41:14

0.013134873 = product of:
  0.039404616 = sum of:
    0.039404616 = product of:
      0.07880923 = sum of:
        0.07880923 = weight(_text_:indexing in 3948) [ClassicSimilarity], result of:
          0.07880923 = score(doc=3948,freq=12.0), product of:
            0.19018644 = queryWeight, product of:
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.049684696 = queryNorm
            0.41437882 = fieldWeight in 3948, product of:
              3.4641016 = tf(freq=12.0), with freq of:
                12.0 = termFreq=12.0
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.03125 = fieldNorm(doc=3948)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

Purpose - This paper sets out to discuss the use of information extraction (IE), a natural language-processing (NLP) technique to assist "rich" semantic indexing of diverse archaeological text resources. The focus of the research is to direct a semantic-aware "rich" indexing of diverse natural language resources with properties capable of satisfying information retrieval from online publications and datasets associated with the Semantic Technologies for Archaeological Resources (STAR) project. Design/methodology/approach - The paper proposes use of the English Heritage extension (CRM-EH) of the standard core ontology in cultural heritage, CIDOC CRM, and exploitation of domain thesauri resources for driving and enhancing an Ontology-Oriented Information Extraction process. The process of semantic indexing is based on a rule-based Information Extraction technique, which is facilitated by the General Architecture of Text Engineering (GATE) toolkit and expressed by Java Annotation Pattern Engine (JAPE) rules. Findings - Initial results suggest that the combination of information extraction with knowledge resources and standard conceptual models is capable of supporting semantic-aware term indexing. Additional efforts are required for further exploitation of the technique and adoption of formal evaluation methods for assessing the performance of the method in measurable terms. Originality/value - The value of the paper lies in the semantic indexing of 535 unpublished online documents often referred to as "Grey Literature", from the Archaeological Data Service OASIS corpus (Online AccesS to the Index of archaeological investigationS), with respect to the CRM ontological concepts E49.Time Appellation and P19.Physical Object.

0.011219318 = product of:
  0.033657953 = sum of:
    0.033657953 = product of:
      0.06731591 = sum of:
        0.06731591 = weight(_text_:22 in 539) [ClassicSimilarity], result of:
          0.06731591 = score(doc=539,freq=2.0), product of:
            0.17398734 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.049684696 = queryNorm
            0.38690117 = fieldWeight in 539, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.078125 = fieldNorm(doc=539)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Date

26.12.2011 13:22:07

0.009479279 = product of:
  0.028437834 = sum of:
    0.028437834 = product of:
      0.05687567 = sum of:
        0.05687567 = weight(_text_:indexing in 2918) [ClassicSimilarity], result of:
          0.05687567 = score(doc=2918,freq=4.0), product of:
            0.19018644 = queryWeight, product of:
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.049684696 = queryNorm
            0.29905218 = fieldWeight in 2918, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.0390625 = fieldNorm(doc=2918)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

Purpose - The purpose of this paper is to explore the potential of applying the Dewey Decimal Classification (DDC) as an established knowledge organization system (KOS) for enhancing social tagging, with the ultimate purpose of improving subject indexing and information retrieval. Design/methodology/approach - Over 11.000 Intute metadata records in politics were used. Totally, 28 politics students were each given four tasks, in which a total of 60 resources were tagged in two different configurations, one with uncontrolled social tags only and another with uncontrolled social tags as well as suggestions from a controlled vocabulary. The controlled vocabulary was DDC comprising also mappings from the Library of Congress Subject Headings. Findings - The results demonstrate the importance of controlled vocabulary suggestions for indexing and retrieval: to help produce ideas of which tags to use, to make it easier to find focus for the tagging, to ensure consistency and to increase the number of access points in retrieval. The value and usefulness of the suggestions proved to be dependent on the quality of the suggestions, both as to conceptual relevance to the user and as to appropriateness of the terminology. Originality/value - No research has investigated the enhancement of social tagging with suggestions from the DDC, an established KOS, in a user trial, comparing social tagging only and social tagging enhanced with the suggestions. This paper is a final reflection on all aspects of the study.

0.009479279 = product of:
  0.028437834 = sum of:
    0.028437834 = product of:
      0.05687567 = sum of:
        0.05687567 = weight(_text_:indexing in 3179) [ClassicSimilarity], result of:
          0.05687567 = score(doc=3179,freq=4.0), product of:
            0.19018644 = queryWeight, product of:
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.049684696 = queryNorm
            0.29905218 = fieldWeight in 3179, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.0390625 = fieldNorm(doc=3179)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

There are many advantages for Digital Libraries in indexing with classifications or thesauri, but some current disincentive in the lack of flexible retrieval tools that deal with compound descriptors. This paper discusses a matching function for compound descriptors, or multi-concept subject headings, that does not rely an exact matching but incorporates term expansion via thesaurus semantic relationships to produce ranked results that take account of missing and partially matching terms. The matching function is based an a measure of semantic closeness between terms, which has the potential to help with recall problems. The work reported is part of the ongoing FACET project in collaboration with the National Museum of Science and Industry and its collections database. The architecture of the prototype system and its Interface are outlined. The matching problem for compound descriptors is reviewed and the FACET implementation described. Results are discussed from scenarios using the faceted Getty Art and Architecture Thesaurus. We argue that automatic traversal of thesaurus relationships can augment the user's browsing possibilities. The techniques can be applied both to unstructured multi-concept subject headings and potentially to more syntactically structured strings. The notion of a focus term is used by the matching function to model AAT modified descriptors (noun phrases). The relevance of the approach to precoordinated indexing and matching faceted strings is discussed.

0.009479279 = product of:
  0.028437834 = sum of:
    0.028437834 = product of:
      0.05687567 = sum of:
        0.05687567 = weight(_text_:indexing in 2300) [ClassicSimilarity], result of:
          0.05687567 = score(doc=2300,freq=4.0), product of:
            0.19018644 = queryWeight, product of:
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.049684696 = queryNorm
            0.29905218 = fieldWeight in 2300, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.0390625 = fieldNorm(doc=2300)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

Subject terms play a crucial role in resource discovery but require substantial effort to produce. Automatic subject classification and indexing address problems of scale and sustainability and can be used to enrich existing bibliographic records, establish more connections across and between resources and enhance consistency of bibliographic data. The paper aims to put forward a complex methodological framework to evaluate automatic classification tools of Swedish textual documents based on the Dewey Decimal Classification (DDC) recently introduced to Swedish libraries. Three major complementary approaches are suggested: a quality-built gold standard, retrieval effects, domain analysis. The gold standard is built based on input from at least two catalogue librarians, end-users expert in the subject, end users inexperienced in the subject and automated tools. Retrieval effects are studied through a combination of assigned and free tasks, including factual and comprehensive types. The study also takes into consideration the different role and character of subject terms in various knowledge domains, such as scientific disciplines. As a theoretical framework, domain analysis is used and applied in relation to the implementation of DDC in Swedish libraries and chosen domains of knowledge within the DDC itself.

0.009479279 = product of:
  0.028437834 = sum of:
    0.028437834 = product of:
      0.05687567 = sum of:
        0.05687567 = weight(_text_:indexing in 2895) [ClassicSimilarity], result of:
          0.05687567 = score(doc=2895,freq=4.0), product of:
            0.19018644 = queryWeight, product of:
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.049684696 = queryNorm
            0.29905218 = fieldWeight in 2895, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.0390625 = fieldNorm(doc=2895)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

The article presents a method for automatic semantic indexing of archaeological grey-literature reports using empirical (rule-based) Information Extraction techniques in combination with domain-specific knowledge organization systems. The semantic annotation system (OPTIMA) performs the tasks of Named Entity Recognition, Relation Extraction, Negation Detection, and Word-Sense Disambiguation using hand-crafted rules and terminological resources for associating contextual abstractions with classes of the standard ontology CIDOC Conceptual Reference Model (CRM) for cultural heritage and its archaeological extension, CRM-EH. Relation Extraction (RE) performance benefits from a syntactic-based definition of RE patterns derived from domain oriented corpus analysis. The evaluation also shows clear benefit in the use of assistive natural language processing (NLP) modules relating to Word-Sense Disambiguation, Negation Detection, and Noun Phrase Validation, together with controlled thesaurus expansion. The semantic indexing results demonstrate the capacity of rule-based Information Extraction techniques to deliver interoperable semantic abstractions (semantic annotations) with respect to the CIDOC CRM and archaeological thesauri. Major contributions include recognition of relevant entities using shallow parsing NLP techniques driven by a complimentary use of ontological and terminological domain resources and empirical derivation of context-driven RE rules for the recognition of semantic relationships from phrases of unstructured text.

0.009384007 = product of:
  0.02815202 = sum of:
    0.02815202 = product of:
      0.05630404 = sum of:
        0.05630404 = weight(_text_:indexing in 2294) [ClassicSimilarity], result of:
          0.05630404 = score(doc=2294,freq=2.0), product of:
            0.19018644 = queryWeight, product of:
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.049684696 = queryNorm
            0.29604656 = fieldWeight in 2294, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.0546875 = fieldNorm(doc=2294)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

Purpose: Investigate the combination of controlled and folksonomy approaches to support resource discovery in repositories and digital collections. Aim: Investigate whether use of an established controlled vocabulary can help improve social tagging for better resource discovery. Objectives: (1) Investigate indexing aspects when using only social tagging versus when using social tagging with suggestions from a controlled vocabulary; (2) Investigate above in two different contexts: tagging by readers and tagging by authors; (3) Investigate influence of only social tagging versus social tagging with a controlled vocabulary on retrieval. - Vgl.: http://www.ukoln.ac.uk/projects/enhanced-tagging/.

0.0075834226 = product of:
  0.022750268 = sum of:
    0.022750268 = product of:
      0.045500536 = sum of:
        0.045500536 = weight(_text_:indexing in 1955) [ClassicSimilarity], result of:
          0.045500536 = score(doc=1955,freq=4.0), product of:
            0.19018644 = queryWeight, product of:
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.049684696 = queryNorm
            0.23924173 = fieldWeight in 1955, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.03125 = fieldNorm(doc=1955)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

Dublin Core recommends controlled terminology for the subject of a resource. Knowledge organization systems (KOS), such as classifications, gazetteers, taxonomies and thesauri, provide controlled vocabularies that organize and structure concepts for indexing, classifying, browsing and search. For example, a thesaurus employs a set of standard semantic relationships (ISO 2788, ISO 5964), and major thesauri have a large entry vocabulary of terms considered equivalent for retrieval purposes. Many KOS have been made available for Web-based access. However, they are often not fully integrated into indexing and search systems and the full potential for networked and programmatic access remains untapped. The lack of standardized access and interchange formats impedes wider use of KOS resources. We developed a Web demonstrator (www.comp.glam.ac.uk/~FACET/webdemo/) for the FACET project (www.comp.glam.ac.uk/~facet/facetproject.html) that explored thesaurus-based query expansion with the Getty Art and Architecture Thesaurus. A Web demonstrator was implemented via Active Server Pages (ASP) with server-side scripting and compiled server-side components for database access, and cascading style sheets for presentation. The browser-based interactive interface permits dynamic control of query term expansion. However, being based on a custom thesaurus representation and API, the techniques cannot be applied directly to thesauri in other formats on the Web. General programmatic access requires commonly agreed protocols, for example, building on Web and Grid services. The development of common KOS representation formats and service protocols are closely linked. Linda Hill and colleagues argued in 2002 for a general KOS service protocol from which protocols for specific types of KOS can be derived. Thus, in the future, a combination of thesaurus and query protocols might permit a thesaurus to be used with a choice of search tools on various kinds of databases. Service-oriented architectures bring an opportunity for moving toward a clearer separation of interface components from the underlying data sources. In our view, basing distributed protocol services on the atomic elements of thesaurus data structures and relationships is not necessarily the best approach because client operations that require multiple client-server calls would carry too much overhead. This would limit the interfaces that could be offered by applications following such a protocol. Advanced interactive interfaces require protocols that group primitive thesaurus data elements (via their relationships) into composites to achieve reasonable response.

0.0067315903 = product of:
  0.02019477 = sum of:
    0.02019477 = product of:
      0.04038954 = sum of:
        0.04038954 = weight(_text_:22 in 1347) [ClassicSimilarity], result of:
          0.04038954 = score(doc=1347,freq=2.0), product of:
            0.17398734 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.049684696 = queryNorm
            0.23214069 = fieldWeight in 1347, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.046875 = fieldNorm(doc=1347)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Date

22. 8.2014 17:12:54

0.0067028617 = product of:
  0.020108584 = sum of:
    0.020108584 = product of:
      0.04021717 = sum of:
        0.04021717 = weight(_text_:indexing in 2215) [ClassicSimilarity], result of:
          0.04021717 = score(doc=2215,freq=2.0), product of:
            0.19018644 = queryWeight, product of:
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.049684696 = queryNorm
            0.21146181 = fieldWeight in 2215, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.0390625 = fieldNorm(doc=2215)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

Purpose - The purpose of this paper is to explore query expansion via conceptual distance in thesaurus indexed collections Design/methodology/approach - An extract of the National Museum of Science and Industry's collections database, indexed with the Getty Art and Architecture Thesaurus (AAT), was the dataset for the research. The system architecture and algorithms for semantic closeness and the matching function are outlined. Standalone and web interfaces are described and formative qualitative user studies are discussed. One user session is discussed in detail, together with a scenario based on a related public inquiry. Findings are set in context of the literature on thesaurus-based query expansion. This paper discusses the potential of query expansion techniques using the semantic relationships in a faceted thesaurus. Findings - Thesaurus-assisted retrieval systems have potential for multi-concept descriptors, permitting very precise queries and indexing. However, indexer and searcher may differ in terminology judgments and there may not be any exactly matching results. The integration of semantic closeness in the matching function permits ranked results for multi-concept queries in thesaurus-indexed applications. An in-memory representation of the thesaurus semantic network allows a combination of automatic and interactive control of expansion and control of expansion on individual query terms. Originality/value - The application of semantic expansion to browsing may be useful in interface options where thesaurus structure is hidden.

0.0067028617 = product of:
  0.020108584 = sum of:
    0.020108584 = product of:
      0.04021717 = sum of:
        0.04021717 = weight(_text_:indexing in 2205) [ClassicSimilarity], result of:
          0.04021717 = score(doc=2205,freq=2.0), product of:
            0.19018644 = queryWeight, product of:
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.049684696 = queryNorm
            0.21146181 = fieldWeight in 2205, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.0390625 = fieldNorm(doc=2205)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

The concept of Linked Data has been an emerging theme within the computing and digital heritage areas in recent years. The growth and scale of Linked Data has underlined the need for greater commonality in concept referencing, to avoid local redefinition and duplication of reference resources. Achieving domain-wide agreement on common vocabularies would be an unreasonable expectation; however, datasets often already have local vocabulary resources defined, and so the prospects for large-scale interoperability can be substantially improved by creating alignment links from these local vocabularies out to common external reference resources. The ARIADNE project is undertaking large-scale integration of archaeology dataset metadata records, to create a cross-searchable research repository resource. Key to enabling this cross search will be the 'subject' metadata originating from multiple data providers, containing terms from multiple multilingual controlled vocabularies. This paper discusses various aspects of vocabulary mapping. Experience from the previous SENESCHAL project in the publication of controlled vocabularies as Linked Open Data is discussed, emphasizing the importance of unique URI identifiers for vocabulary concepts. There is a need to align legacy indexing data to the uniquely defined concepts and examples are discussed of SENESCHAL data alignment work. A case study for the ARIADNE project presents work on mapping between vocabularies, based on the Getty Art and Architecture Thesaurus as a central hub and employing an interactive vocabulary mapping tool developed for the project, which generates SKOS mapping relationships in JSON and other formats. The potential use of such vocabulary mappings to assist cross search over archaeological datasets from different countries is illustrated in a pilot experiment. The results demonstrate the enhanced opportunities for interoperability and cross searching that the approach offers.

0.0067028617 = product of:
  0.020108584 = sum of:
    0.020108584 = product of:
      0.04021717 = sum of:
        0.04021717 = weight(_text_:indexing in 600) [ClassicSimilarity], result of:
          0.04021717 = score(doc=600,freq=2.0), product of:
            0.19018644 = queryWeight, product of:
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.049684696 = queryNorm
            0.21146181 = fieldWeight in 600, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.0390625 = fieldNorm(doc=600)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

Purpose The Integrative Levels Classification (ILC) is a comprehensive "freely faceted" knowledge organization system not previously expressed as SKOS (Simple Knowledge Organization System). This paper reports and reflects on work converting the ILC to SKOS representation. Design/methodology/approach The design of the ILC representation and the various steps in the conversion to SKOS are described and located within the context of previous work considering the representation of complex classification schemes in SKOS. Various issues and trade-offs emerging from the conversion are discussed. The conversion implementation employed the STELETO transformation tool. Findings The ILC conversion captures some of the ILC facet structure by a limited extension beyond the SKOS standard. SPARQL examples illustrate how this extension could be used to create faceted, compound descriptors when indexing or cataloguing. Basic query patterns are provided that might underpin search systems. Possible routes for reducing complexity are discussed. Originality/value Complex classification schemes, such as the ILC, have features which are not straight forward to represent in SKOS and which extend beyond the functionality of the SKOS standard. The ILC's facet indicators are modelled as rdf:Property sub-hierarchies that accompany the SKOS RDF statements. The ILC's top-level fundamental facet relationships are modelled by extensions of the associative relationship - specialised sub-properties of skos:related. An approach for representing faceted compound descriptions in ILC and other faceted classification schemes is proposed.

0.00536229 = product of:
  0.016086869 = sum of:
    0.016086869 = product of:
      0.032173738 = sum of:
        0.032173738 = weight(_text_:indexing in 175) [ClassicSimilarity], result of:
          0.032173738 = score(doc=175,freq=2.0), product of:
            0.19018644 = queryWeight, product of:
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.049684696 = queryNorm
            0.16916946 = fieldWeight in 175, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.03125 = fieldNorm(doc=175)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Abstract

There are many advantages for Digital Libraries in indexing with classifications or thesauri, but some current disincentive in the lack of flexible retrieval tools that deal with compound descriptors. This demonstration of a research prototype illustrates a matching function for compound descriptors, or multi-concept subject headings, that does not rely on exact matching but incorporates term expansion via thesaurus semantic relationships to produce ranked results that take account of missing and partially matching terms. The matching function is based on a measure of semantic closeness between terms.The work is part of the EPSRC funded FACET project in collaboration with the UK National Museum of Science and Industry (NMSI) which includes the National Railway Museum. An export of NMSI's Collections Database is used as the dataset for the research. The J. Paul Getty Trust's Art and Architecture Thesaurus (AAT) is the main thesaurus in the project. The AAT is a widely used thesaurus (over 120,000 terms). Descriptors are organised in 7 facets representing separate conceptual classes of terms.The FACET application is a multi tiered architecture accessing a SQL Server database, with an OLE DB connection. The thesauri are stored as relational tables in the Server's database. However, a key component of the system is a parallel representation of the underlying semantic network as an in-memory structure of thesaurus concepts (corresponding to preferred terms). The structure models the hierarchical and associative interrelationships of thesaurus concepts via weighted poly-hierarchical links. Its primary purpose is real-time semantic expansion of query terms, achieved by a spreading activation semantic closeness algorithm. Queries with associated results are stored persistently using XML format data. A Visual Basic interface combines a thesaurus browser and an initial term search facility that takes into account equivalence relationships. Terms are dragged to a direct manipulation Query Builder which maintains the facet structure.

0.0046920036 = product of:
  0.01407601 = sum of:
    0.01407601 = product of:
      0.02815202 = sum of:
        0.02815202 = weight(_text_:indexing in 2677) [ClassicSimilarity], result of:
          0.02815202 = score(doc=2677,freq=2.0), product of:
            0.19018644 = queryWeight, product of:
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.049684696 = queryNorm
            0.14802328 = fieldWeight in 2677, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.8278677 = idf(docFreq=2614, maxDocs=44218)
              0.02734375 = fieldNorm(doc=2677)
      0.5 = coord(1/2)
  0.33333334 = coord(1/3)

Content

1. Introduction The need for research into the application of linguistic techniques in Information Retrieval (IR) in general, and a similar need in faceted Knowledge Organization Systems (KOS) has been indicated by various authors. Smeaton (1997) points out the inherent limitations of conventional approaches to IR based an "bags of words", mainly difficulties caused by lexical ambiguity in the words concerned, and goes an to suggest the possibility of using Natural Language Processing (NLP) in query formulation. Past experience with a faceted retrieval system highlighted the need for integrating the linguistic perspective in order to fully utilise the potential of a KOS (Tudhope et al." 2002). The present research seeks to address some of these needs in using NLP to improve the efficacy of KOS tools in query and retrieval systems. Syntactic parsing and part-of-speech tagging can substantially reduce lexical ambiguity through homograph disambiguation. Given the two strings "1 fable the motion" and "I put the motion an the fable", for instance, the parser used in this research clearly indicates that 'fable' in the first string is a verb, while 'table' in the second string is a noun, a distinction that would be missed in the "bag of words" approach. This syntactic disambiguation enables a more precise matching from free text to the controlled vocabulary of a KOS and vice versa. The use of a general linguistic resource, namely Roget's Thesaurus of English Words and Phrases (RTEWP), as an intermediary in this process, is investigated. The adaptation of the Link parser (Sleator & Temperley, 1993) to the purposes of the research is reported. The design and implementation of the early practical stages of the project are described, and the results of the initial experiments are presented and evaluated. Applications of the techniques developed are foreseen in the areas of query disambiguation, information retrieval and automatic indexing. In the first section of the paper a brief review of the literature and relevant current work in the field is presented. The second section includes reports an the development of algorithms, the construction of data sets and theoretical and experimental work undertaken to date. The third section evaluates the results obtained, and outlines directions for future research.