Search (213 results, page 3 of 11)

0.00270615 = product of:
  0.0054123 = sum of:
    0.0054123 = product of:
      0.0108246 = sum of:
        0.0108246 = weight(_text_:a in 3845) [ClassicSimilarity], result of:
          0.0108246 = score(doc=3845,freq=8.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.20383182 = fieldWeight in 3845, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0625 = fieldNorm(doc=3845)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

2 studies were conducted to investigate the cognitive processes involved in online document-based information retrieval. These studies led to the development of 5 computerised models of online document retrieval. These models were incorporated into a design of an 'intelligent' document-based retrieval system. Following a discussion of this system, discusses the broader implications of the research for the design of information retrieval sysems

Type

a

0.00270615 = product of:
  0.0054123 = sum of:
    0.0054123 = product of:
      0.0108246 = sum of:
        0.0108246 = weight(_text_:a in 5400) [ClassicSimilarity], result of:
          0.0108246 = score(doc=5400,freq=2.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.20383182 = fieldWeight in 5400, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.125 = fieldNorm(doc=5400)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Type

a

0.00270615 = product of:
  0.0054123 = sum of:
    0.0054123 = product of:
      0.0108246 = sum of:
        0.0108246 = weight(_text_:a in 6891) [ClassicSimilarity], result of:
          0.0108246 = score(doc=6891,freq=2.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.20383182 = fieldWeight in 6891, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.125 = fieldNorm(doc=6891)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Type

a

0.00270615 = product of:
  0.0054123 = sum of:
    0.0054123 = product of:
      0.0108246 = sum of:
        0.0108246 = weight(_text_:a in 7683) [ClassicSimilarity], result of:
          0.0108246 = score(doc=7683,freq=2.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.20383182 = fieldWeight in 7683, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.125 = fieldNorm(doc=7683)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Type

a

0.00270615 = product of:
  0.0054123 = sum of:
    0.0054123 = product of:
      0.0108246 = sum of:
        0.0108246 = weight(_text_:a in 1915) [ClassicSimilarity], result of:
          0.0108246 = score(doc=1915,freq=8.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.20383182 = fieldWeight in 1915, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0625 = fieldNorm(doc=1915)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

The conference was attended by about 150 people involved in 31 participating groups. Its goal was to bring research groups together to discuss their work on a new large test collection. There was a large variation of retrieval techniques reported on, including methods using automatic thesauri, sophisticated term weighting, natural language techniques, relevance feedback, and advanced pattern matching. As results had been run through a common evaluation package, groups were able to compare the effectiveness of different techniques, and discuss how differences between the systems affected performance

Type

a

0.00270615 = product of:
  0.0054123 = sum of:
    0.0054123 = product of:
      0.0108246 = sum of:
        0.0108246 = weight(_text_:a in 3850) [ClassicSimilarity], result of:
          0.0108246 = score(doc=3850,freq=8.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.20383182 = fieldWeight in 3850, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0625 = fieldNorm(doc=3850)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Aims to determine the extent to which there is a core of relevance criteria that soans such factors as information need situations, user environments, and types of information. 2 recent empirical studies have identified and described user defined relevance criteria. Synthesizes the findings of the 2 studies as a 1st step toward identifying criteria that seem to span information environments and criteria that may be more situationally specific

Type

a

0.00270615 = product of:
  0.0054123 = sum of:
    0.0054123 = product of:
      0.0108246 = sum of:
        0.0108246 = weight(_text_:a in 414) [ClassicSimilarity], result of:
          0.0108246 = score(doc=414,freq=2.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.20383182 = fieldWeight in 414, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.125 = fieldNorm(doc=414)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Type

a

0.0026849252 = product of:
  0.0053698504 = sum of:
    0.0053698504 = product of:
      0.010739701 = sum of:
        0.010739701 = weight(_text_:a in 2323) [ClassicSimilarity], result of:
          0.010739701 = score(doc=2323,freq=14.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.20223314 = fieldWeight in 2323, product of:
              3.7416575 = tf(freq=14.0), with freq of:
                14.0 = termFreq=14.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046875 = fieldNorm(doc=2323)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Partial coordination is a new method for cataloging documents for subject access. It is especially designed to enhance the precision of document searches in online environments. This article reports a preliminary evaluation of partial coordination that shows promising results compared with full-text retrieval. We also report the difficulties in empirically evaluating the effectiveness of automatic full-text retrieval in contrast to mixed methods such as partial coordination which combine human cataloging with computerized retrieval. Based on our study, we propose research in this area will substantially benefit from a common framework for failure analysis and a common data set. This will allow information retrieval researchers adapting 'library style'cataloging to large electronic document collections, as well as those developing automated or mixed methods, to directly compare their proposals for indexing and retrieval. This article concludes by suggesting guidelines for constructing such as testbed

Type

a

0.0026849252 = product of:
  0.0053698504 = sum of:
    0.0053698504 = product of:
      0.010739701 = sum of:
        0.010739701 = weight(_text_:a in 5696) [ClassicSimilarity], result of:
          0.010739701 = score(doc=5696,freq=14.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.20223314 = fieldWeight in 5696, product of:
              3.7416575 = tf(freq=14.0), with freq of:
                14.0 = termFreq=14.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046875 = fieldNorm(doc=5696)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Shows how probabilistic information retrieval based on document components may be implemented as a feedforward (feedbackward) artificial neural network. The network supports adaptation of connection weights as well as the growing of new edges between queries and terms based on user relevance feedback data for training, and it reflects query modification and expansion in information retrieval. A learning rule is applied that can also be viewed as supporting sequential learning using a harmonic sequence learning rate. Experimental results with 4 standard small collections and a large Wall Street Journal collection show that small query expansion levels of about 30 terms can achieve most of the gains at the low-recall high-precision region, while larger expansion levels continue to provide gains at the high-recall low-precision region of a precision recall curve

Type

a

0.0026849252 = product of:
  0.0053698504 = sum of:
    0.0053698504 = product of:
      0.010739701 = sum of:
        0.010739701 = weight(_text_:a in 5699) [ClassicSimilarity], result of:
          0.010739701 = score(doc=5699,freq=14.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.20223314 = fieldWeight in 5699, product of:
              3.7416575 = tf(freq=14.0), with freq of:
                14.0 = termFreq=14.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046875 = fieldNorm(doc=5699)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

The Smart information retrieval project emphazises completely automatic approaches to the understanding and retrieval of large quantities of text. The work in the TREC-2 environment continues, performing both routing and ad hoc experiments. The ad hoc work extends investigations into combining global similarities, giving an overall indication of how a document matches a query, with local similarities identifying a smaller part of the document that matches the query. The performance of ad hoc runs is good, but it is clear that full advantage of the available local information is not been taken advantage of. The routing experiments use conventional relevance feedback approaches to routing, but with a much greater degree of query expansion than was previously done. The length of a query vector is increased by a factor of 5 to 10 by adding terms found in previously seen relevant documents. This approach improves effectiveness by 30-40% over the original query

Type

a

0.0026473717 = product of:
  0.0052947435 = sum of:
    0.0052947435 = product of:
      0.010589487 = sum of:
        0.010589487 = weight(_text_:a in 3114) [ClassicSimilarity], result of:
          0.010589487 = score(doc=3114,freq=10.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.19940455 = fieldWeight in 3114, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0546875 = fieldNorm(doc=3114)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Addresses the problem of how potential users of CD-ROM data bases can objectively establish which version of the same data base is best suited for a specific situation. The problem was solved by applying the retrieval effectiveness of current on-line data base search systems as a standard measurement. 5 search queries from the medical sciences were presented by experienced users of MEDLINE. Search strategies were written for both DIALOG and DATA-STAR. Search results were compared to create a recall base from documents present in both on-line searches. This recall base was then used to establish the retrieval and precision of 4 CD-ROM data bases: MEDLINE, Compact Cambrdge MEDLINE, DIALOG OnDisc, Comprehensive MEDLINE/EBSCO

Type

a

0.0026473717 = product of:
  0.0052947435 = sum of:
    0.0052947435 = product of:
      0.010589487 = sum of:
        0.010589487 = weight(_text_:a in 4276) [ClassicSimilarity], result of:
          0.010589487 = score(doc=4276,freq=10.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.19940455 = fieldWeight in 4276, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0546875 = fieldNorm(doc=4276)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Examines judgements of relevance of document representations to query statements made by people other than the the originators of the queries. A small group of graduate students in the School of Information and Library Studies and undergraduates of Michigan Univ. judges sets of documents that had been retrieved for and judged by real users for a previous study. The assessment of relevance, by the secondary judges, were analysed by themselves and in comparison with the users' assessments. The judges performed reasonably well but some important differences were identified. Secondary judges use the various fields of document records in different ways than users and have a higher threshold of relevance

Type

a

0.0026473717 = product of:
  0.0052947435 = sum of:
    0.0052947435 = product of:
      0.010589487 = sum of:
        0.010589487 = weight(_text_:a in 2651) [ClassicSimilarity], result of:
          0.010589487 = score(doc=2651,freq=10.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.19940455 = fieldWeight in 2651, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0546875 = fieldNorm(doc=2651)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Few studies have compared the interactive use of Boolean and natural language search systems. Studies the use of 3 retrieval systems by senior medical students searching on queries generated by actual physicians in a clinical setting. The searchers were randomized to search on 2 or 3 different retrieval systems: a Boolean system, a word-based natural language system, and a concept-based natural language system. Results showed no statistically significant differences in recall or precision among the 3 systems. Likewise, there is no user preference for any system over the other. The study revealed problems with traditional measures of retrieval evaluation when applied to the interactive search setting

Type

a

0.0026473717 = product of:
  0.0052947435 = sum of:
    0.0052947435 = product of:
      0.010589487 = sum of:
        0.010589487 = weight(_text_:a in 6622) [ClassicSimilarity], result of:
          0.010589487 = score(doc=6622,freq=10.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.19940455 = fieldWeight in 6622, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0546875 = fieldNorm(doc=6622)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Investigates how linkage environments in a hypertext based bibliographic retrieval system affect retrieval performance for novice and experienced searchers, 2 systems, 1 with inter record linkages to authors and descriptors and 1 that also included title and abstract keywords, were tested. No significant differences in retrieval performance and system usage were found for most search tests. The enhanced system did provide better performance where title and abstract keywords provided the most direct access to relevant records. The findings have implications for the design of bilbiographic information retrieval systems using hypertext linkages

Type

a

0.0026473717 = product of:
  0.0052947435 = sum of:
    0.0052947435 = product of:
      0.010589487 = sum of:
        0.010589487 = weight(_text_:a in 6634) [ClassicSimilarity], result of:
          0.010589487 = score(doc=6634,freq=10.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.19940455 = fieldWeight in 6634, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0546875 = fieldNorm(doc=6634)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

The indexing vocabulary is an important determinant of success in text retrieval. Researchers have compared the effectiveness of indexing using free text and controlled vocabularies in a variety of text contexts. A number of studies have investigated the relative merits of free-text, MeSH and UMLS metathesaurus indexing vocabularies for MEDLINE document indexing. Controlled vocabularies offer no advantages in retrieval performance over free text. Offers a detailed analysis of prior results and their underlying experimental designs. Offers results from a new experiment assessing 8 different retrieval strategies. Results indicate that MeSH does have an important role in text retrieval

Type

a

0.0026473717 = product of:
  0.0052947435 = sum of:
    0.0052947435 = product of:
      0.010589487 = sum of:
        0.010589487 = weight(_text_:a in 956) [ClassicSimilarity], result of:
          0.010589487 = score(doc=956,freq=10.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.19940455 = fieldWeight in 956, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0546875 = fieldNorm(doc=956)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

This article describes a series of experiments with an interactive Chinese information retrieval system named CIRS and an interactive relational thesaurus. 2 important issues have been explored: whether thesauri enhance the retrieval effectiveness of Chinese documents, and whether automatic indexing can complete with manual indexing in a Chinese information retrieval system. Recall and precision are used to measure and evaluate the effectiveness of the system. Statistical analysis of the recall and precision measures suggest that the use of the relational thesaurus does improve the retrieval effectiveness both in the automatic indexing environment and in the manual indexing environment and that automatic indexing is at least as good as manual indexing

Type

a

0.0026473717 = product of:
  0.0052947435 = sum of:
    0.0052947435 = product of:
      0.010589487 = sum of:
        0.010589487 = weight(_text_:a in 1314) [ClassicSimilarity], result of:
          0.010589487 = score(doc=1314,freq=10.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.19940455 = fieldWeight in 1314, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0546875 = fieldNorm(doc=1314)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

The Text REtrieval Conference (TREC) workshop series encourages research in information retrieval from large text applications by providing a large test collection, uniform scoring procedures and a forum for organizations interested in comparing their results. Now in its seventh year, the conference has become the major experimental effort in the field. Participants in the TREC conferences have examined a wide variety of retrieval techniques, including methods using automatic thesauri, sophisticated term weighting, natural language techniques, relevance feedback and advanced pattern matching. The TREC conference series is co-sponsored by the National Institute of Standards and Technology (NIST) and the Information Technology Office of the Defense Advanced Research Projects Agency (DARPA)

Type

a

0.0026473717 = product of:
  0.0052947435 = sum of:
    0.0052947435 = product of:
      0.010589487 = sum of:
        0.010589487 = weight(_text_:a in 340) [ClassicSimilarity], result of:
          0.010589487 = score(doc=340,freq=10.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.19940455 = fieldWeight in 340, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0546875 = fieldNorm(doc=340)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Report of a study from the user's point of view, investigating the facility with which bibliographical material can be identified in a multidisciplinary field, the prospective for peace, from the University's resources. Searches (uniterm and relational) were effected using all available tools - OPACs, CD-ROM collections, online databases, manual catalogues, the Internet - both on the University's system and on national research institutions. Overall results returned a low rate of pertinence (1,86%). This is due not to lack of user search expertise but the lack of subject specific indexing coupled with using a MARC format

Type

a

0.0025720107 = product of:
  0.0051440215 = sum of:
    0.0051440215 = product of:
      0.010288043 = sum of:
        0.010288043 = weight(_text_:a in 6299) [ClassicSimilarity], result of:
          0.010288043 = score(doc=6299,freq=74.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.19372822 = fieldWeight in 6299, product of:
              8.602325 = tf(freq=74.0), with freq of:
                74.0 = termFreq=74.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.01953125 = fieldNorm(doc=6299)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Content

Enthält die Beiträge: GREFENSTETTE, G.: The Problem of Cross-Language Information Retrieval; DAVIS, M.W.: On the Effective Use of Large Parallel Corpora in Cross-Language Text Retrieval; BALLESTEROS, L. u. W.B. CROFT: Statistical Methods for Cross-Language Information Retrieval; Distributed Cross-Lingual Information Retrieval; Automatic Cross-Language Information Retrieval Using Latent Semantic Indexing; EVANS, D.A. u.a.: Mapping Vocabularies Using Latent Semantics; PICCHI, E. u. C. PETERS: Cross-Language Information Retrieval: A System for Comparable Corpus Querying; YAMABANA, K. u.a.: A Language Conversion Front-End for Cross-Language Information Retrieval; GACHOT, D.A. u.a.: The Systran NLP Browser: An Application of Machine Translation Technology in Cross-Language Information Retrieval; HULL, D.: A Weighted Boolean Model for Cross-Language Text Retrieval; SHERIDAN, P. u.a. Building a Large Multilingual Test Collection from Comparable News Documents; OARD; D.W. u. B.J. DORR: Evaluating Cross-Language Text Filtering Effectiveness

Footnote

Rez. in: Machine translation review: 1999, no.10, S.26-27 (D. Lewis): "Cross Language Information Retrieval (CLIR) addresses the growing need to access large volumes of data across language boundaries. The typical requirement is for the user to input a free form query, usually a brief description of a topic, into a search or retrieval engine which returns a list, in ranked order, of documents or web pages that are relevant to the topic. The search engine matches the terms in the query to indexed terms, usually keywords previously derived from the target documents. Unlike monolingual information retrieval, CLIR requires query terms in one language to be matched to indexed terms in another. Matching can be done by bilingual dictionary lookup, full machine translation, or by applying statistical methods. A query's success is measured in terms of recall (how many potentially relevant target documents are found) and precision (what proportion of documents found are relevant). Issues in CLIR are how to translate query terms into index terms, how to eliminate alternative translations (e.g. to decide that French 'traitement' in a query means 'treatment' and not 'salary'), and how to rank or weight translation alternatives that are retained (e.g. how to order the French terms 'aventure', 'business', 'affaire', and 'liaison' as relevant translations of English 'affair'). Grefenstette provides a lucid and useful overview of the field and the problems. The volume brings together a number of experiments and projects in CLIR. Mark Davies (New Mexico State University) describes Recuerdo, a Spanish retrieval engine which reduces translation ambiguities by scanning indexes for parallel texts; it also uses either a bilingual dictionary or direct equivalents from a parallel corpus in order to compare results for queries on parallel texts. Lisa Ballesteros and Bruce Croft (University of Massachusetts) use a 'local feedback' technique which automatically enhances a query by adding extra terms to it both before and after translation; such terms can be derived from documents known to be relevant to the query.
Christian Fluhr at al (DIST/SMTI, France) outline the EMIR (European Multilingual Information Retrieval) and ESPRIT projects. They found that using SYSTRAN to machine translate queries and to access material from various multilingual databases produced less relevant results than a method referred to as 'multilingual reformulation' (the mechanics of which are only hinted at). An interesting technique is Latent Semantic Indexing (LSI), described by Michael Littman et al (Brown University) and, most clearly, by David Evans et al (Carnegie Mellon University). LSI involves creating matrices of documents and the terms they contain and 'fitting' related documents into a reduced matrix space. This effectively allows queries to be mapped onto a common semantic representation of the documents. Eugenio Picchi and Carol Peters (Pisa) report on a procedure to create links between translation equivalents in an Italian-English parallel corpus. The links are used to construct parallel linguistic contexts in real-time for any term or combination of terms that is being searched for in either language. Their interest is primarily lexicographic but they plan to apply the same procedure to comparable corpora, i.e. to texts which are not translations of each other but which share the same domain. Kiyoshi Yamabana et al (NEC, Japan) address the issue of how to disambiguate between alternative translations of query terms. Their DMAX (double maximise) method looks at co-occurrence frequencies between both source language words and target language words in order to arrive at the most probable translation. The statistical data for the decision are derived, not from the translation texts but independently from monolingual corpora in each language. An interactive user interface allows the user to influence the selection of terms during the matching process. Denis Gachot et al (SYSTRAN) describe the SYSTRAN NLP browser, a prototype tool which collects parsing information derived from a text or corpus previously translated with SYSTRAN. The user enters queries into the browser in either a structured or free form and receives grammatical and lexical information about the source text and/or its translation.
The retrieved output from a query including the phrase 'big rockets' may be, for instance, a sentence containing 'giant rocket' which is semantically ranked above 'military ocket'. David Hull (Xerox Research Centre, Grenoble) describes an implementation of a weighted Boolean model for Spanish-English CLIR. Users construct Boolean-type queries, weighting each term in the query, which is then translated by an on-line dictionary before being applied to the database. Comparisons with the performance of unweighted free-form queries ('vector space' models) proved encouraging. Two contributions consider the evaluation of CLIR systems. In order to by-pass the time-consuming and expensive process of assembling a standard collection of documents and of user queries against which the performance of an CLIR system is manually assessed, Páriac Sheridan et al (ETH Zurich) propose a method based on retrieving 'seed documents'. This involves identifying a unique document in a database (the 'seed document') and, for a number of queries, measuring how fast it is retrieved. The authors have also assembled a large database of multilingual news documents for testing purposes. By storing the (fairly short) documents in a structured form tagged with descriptor codes (e.g. for topic, country and area), the test suite is easily expanded while remaining consistent for the purposes of testing. Douglas Ouard and Bonne Dorr (University of Maryland) describe an evaluation methodology which appears to apply LSI techniques in order to filter and rank incoming documents designed for testing CLIR systems. The volume provides the reader an excellent overview of several projects in CLIR. It is well supported with references and is intended as a secondary text for researchers and practitioners. It highlights the need for a good, general tutorial introduction to the field."

0.0025370158 = product of:
  0.0050740317 = sum of:
    0.0050740317 = product of:
      0.010148063 = sum of:
        0.010148063 = weight(_text_:a in 4721) [ClassicSimilarity], result of:
          0.010148063 = score(doc=4721,freq=18.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.19109234 = fieldWeight in 4721, product of:
              4.2426405 = tf(freq=18.0), with freq of:
                18.0 = termFreq=18.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=4721)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

In order to compare the value of subject descriptors and title keywords as entries to subject searches, two studies were carried out. Both studies concentrated on monographs in the humanities and social sciences, held by the online public access catalogue of the National Library of the Netherlands. In the first study, a comparison was made by subject librarians between the subject descriptors and the title keywords of 475 records. They could express their opinion on a scale from 1 (descriptor is exactly or almost the same as word in title) to 7 (descriptor does not appear in title at all). It was concluded that 37 per cent of the records are considerably enhanced by a subject descriptor, and 49 per cent slightly or considerably enhanced. In the second study, subject librarians performed subject searches using title keywords and subject descriptors on the same topic. The relative recall amounted to 48 per cent and 86 per cent respectively. Failure analysis revealed the reasons why so many records that were found by subject descriptors were not found by title keywords. First, although completely meaningless titles hardly ever appear, the title of a publication does not always offer sufficient clues for title keyword searching. In those cases, descriptors may enhance the record of a publication. A second and even more important task of subject descriptors is controlling the vocabulary. Many relevant titles cannot be retrieved by title keyword searching because of the wide diversity of ways of expressing a topic. Descriptors take away the burden of vocabulary control from the user.

Type

a