Search (30 results, page 1 of 2)

  • × author_ss:"Croft, W.B."
  1. Croft, W.B.: Approaches to intelligent information retrieval (1987) 0.01
    0.0067306077 = product of:
      0.02692243 = sum of:
        0.02692243 = weight(_text_:information in 1094) [ClassicSimilarity], result of:
          0.02692243 = score(doc=1094,freq=4.0), product of:
            0.06134496 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.034944877 = queryNorm
            0.43886948 = fieldWeight in 1094, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.125 = fieldNorm(doc=1094)
      0.25 = coord(1/4)
    
    Source
    Information processing and management. 23(1987), S.249-254
  2. Belkin, N.J.; Croft, W.B.: Information filtering and information retrieval : two sides of the same coin? (1992) 0.01
    0.006182458 = product of:
      0.024729831 = sum of:
        0.024729831 = weight(_text_:information in 6093) [ClassicSimilarity], result of:
          0.024729831 = score(doc=6093,freq=6.0), product of:
            0.06134496 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.034944877 = queryNorm
            0.40312737 = fieldWeight in 6093, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.09375 = fieldNorm(doc=6093)
      0.25 = coord(1/4)
    
    Abstract
    One of nine articles in this issue of Communications of the ACM devoted to information filtering
  3. Ballesteros, L.; Croft, W.B.: Statistical methods for cross-language information retrieval (1998) 0.01
    0.006182458 = product of:
      0.024729831 = sum of:
        0.024729831 = weight(_text_:information in 6303) [ClassicSimilarity], result of:
          0.024729831 = score(doc=6303,freq=6.0), product of:
            0.06134496 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.034944877 = queryNorm
            0.40312737 = fieldWeight in 6303, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.09375 = fieldNorm(doc=6303)
      0.25 = coord(1/4)
    
    Series
    The Kluwer International series on information retrieval
    Source
    Cross-language information retrieval. Ed.: G. Grefenstette
  4. Croft, W.B.: Advances in information retrieval : Recent research from the Center for Intelligent Information Retrieval (2000) 0.01
    0.0059192525 = product of:
      0.02367701 = sum of:
        0.02367701 = weight(_text_:information in 6860) [ClassicSimilarity], result of:
          0.02367701 = score(doc=6860,freq=22.0), product of:
            0.06134496 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.034944877 = queryNorm
            0.38596505 = fieldWeight in 6860, product of:
              4.690416 = tf(freq=22.0), with freq of:
                22.0 = termFreq=22.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.046875 = fieldNorm(doc=6860)
      0.25 = coord(1/4)
    
    Content
    Enthält die Beiträge: CROFT, W.B.: Combining approaches to information retrieval; GREIFF, W.R.: The use of exploratory data analysis in information retrieval research; PONTE, J.M.: Language models for relevance feedback; PAPKA, R. u. J. ALLAN: Topic detection and tracking: event clustering as a basis for first story detection; CALLAN, J.: Distributed information retrieval; XU, J. u. W.B. CROFT: Topic-based language models for ditributed retrieval; LU, Z. u. K.S. McKINLEY: The effect of collection organization and query locality on information retrieval system performance; BALLESTEROS, L.A.: Cross-language retrieval via transitive translation; SANDERSON, M. u. D. LAWRIE: Building, testing, and applying concept hierarchies; RAVELA, S. u. C. LUO: Appearance-based global similarity retrieval of images
    Footnote
    Information retrieval - Relevanz - Information Retrieval Systeme - Verteilte Systeme - Multimedia - Bildverarbeitung
    LCSH
    Information retrieval
    Series
    The Kluwer international series on information retrieval; 7
    Subject
    Information retrieval
  5. Croft, W.B.; Metzler, D.; Strohman, T.: Search engines : information retrieval in practice (2010) 0.01
    0.0059192525 = product of:
      0.02367701 = sum of:
        0.02367701 = weight(_text_:information in 2605) [ClassicSimilarity], result of:
          0.02367701 = score(doc=2605,freq=22.0), product of:
            0.06134496 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.034944877 = queryNorm
            0.38596505 = fieldWeight in 2605, product of:
              4.690416 = tf(freq=22.0), with freq of:
                22.0 = termFreq=22.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.046875 = fieldNorm(doc=2605)
      0.25 = coord(1/4)
    
    Abstract
    For introductory information retrieval courses at the undergraduate and graduate level in computer science, information science and computer engineering departments. Written by a leader in the field of information retrieval, Search Engines: Information Retrieval in Practice, is designed to give undergraduate students the understanding and tools they need to evaluate, compare and modify search engines. Coverage of the underlying IR and mathematical models reinforce key concepts. The book's numerous programming exercises make extensive use of Galago, a Java-based open source search engine. SUPPLEMENTS / Extensive lecture slides (in PDF and PPT format) / Solutions to selected end of chapter problems (Instructors only) / Test collections for exercises / Galago search engine
    LCSH
    Information retrieval
    Information Storage and Retrieval
    RSWK
    Suchmaschine / Information Retrieval
    Subject
    Suchmaschine / Information Retrieval
    Information retrieval
    Information Storage and Retrieval
  6. Xiaoyan Li, X.; Croft, W.B.: ¬An information-pattern-based approach to novelty detection (2008) 0.01
    0.0050479556 = product of:
      0.020191822 = sum of:
        0.020191822 = weight(_text_:information in 2080) [ClassicSimilarity], result of:
          0.020191822 = score(doc=2080,freq=16.0), product of:
            0.06134496 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.034944877 = queryNorm
            0.3291521 = fieldWeight in 2080, product of:
              4.0 = tf(freq=16.0), with freq of:
                16.0 = termFreq=16.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.046875 = fieldNorm(doc=2080)
      0.25 = coord(1/4)
    
    Abstract
    In this paper, a new novelty detection approach based on the identification of sentence level information patterns is proposed. First, "novelty" is redefined based on the proposed information patterns, and several different types of information patterns are given corresponding to different types of users' information needs. Second, a thorough analysis of sentence level information patterns is elaborated using data from the TREC novelty tracks, including sentence lengths, named entities (NEs), and sentence level opinion patterns. Finally, a unified information-pattern-based approach to novelty detection (ip-BAND) is presented for both specific NE topics and more general topics. Experiments on novelty detection on data from the TREC 2002, 2003 and 2004 novelty tracks show that the proposed approach significantly improves the performance of novelty detection in terms of precision at top ranks. Future research directions are suggested.
    Source
    Information processing and management. 44(2008) no.3, S.1159-1188
  7. Croft, W.B.; Lucia, T.J.; Cringean, J.: Retrieving documents by plausible inference : an experimental study (1989) 0.00
    0.004759258 = product of:
      0.019037032 = sum of:
        0.019037032 = weight(_text_:information in 3915) [ClassicSimilarity], result of:
          0.019037032 = score(doc=3915,freq=2.0), product of:
            0.06134496 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.034944877 = queryNorm
            0.3103276 = fieldWeight in 3915, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.125 = fieldNorm(doc=3915)
      0.25 = coord(1/4)
    
    Source
    Information processing and management. 25(1989) no.6, S.519-614
  8. Croft, W.B.; Turtle, H.R.: Retrieval strategies for hypertext (1993) 0.00
    0.004759258 = product of:
      0.019037032 = sum of:
        0.019037032 = weight(_text_:information in 4711) [ClassicSimilarity], result of:
          0.019037032 = score(doc=4711,freq=2.0), product of:
            0.06134496 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.034944877 = queryNorm
            0.3103276 = fieldWeight in 4711, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.125 = fieldNorm(doc=4711)
      0.25 = coord(1/4)
    
    Source
    Information processing and management. 29(1993) no.3, S.313-324
  9. Croft, W.B.: Clustering large files of documents using the single link method (1977) 0.00
    0.004759258 = product of:
      0.019037032 = sum of:
        0.019037032 = weight(_text_:information in 5489) [ClassicSimilarity], result of:
          0.019037032 = score(doc=5489,freq=2.0), product of:
            0.06134496 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.034944877 = queryNorm
            0.3103276 = fieldWeight in 5489, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.125 = fieldNorm(doc=5489)
      0.25 = coord(1/4)
    
    Source
    Journal of the American Society for Information Science. 28(1977), S.341-344
  10. Belkin, N.J.; Croft, W.B.: Retrieval techniques (1987) 0.00
    0.004759258 = product of:
      0.019037032 = sum of:
        0.019037032 = weight(_text_:information in 334) [ClassicSimilarity], result of:
          0.019037032 = score(doc=334,freq=2.0), product of:
            0.06134496 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.034944877 = queryNorm
            0.3103276 = fieldWeight in 334, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.125 = fieldNorm(doc=334)
      0.25 = coord(1/4)
    
    Source
    Annual review of information science and technology. 22(1987), S.109-145
  11. Rajashekar, T.B.; Croft, W.B.: Combining automatic and manual index representations in probabilistic retrieval (1995) 0.00
    0.004655886 = product of:
      0.018623544 = sum of:
        0.018623544 = weight(_text_:information in 2418) [ClassicSimilarity], result of:
          0.018623544 = score(doc=2418,freq=10.0), product of:
            0.06134496 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.034944877 = queryNorm
            0.3035872 = fieldWeight in 2418, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.0546875 = fieldNorm(doc=2418)
      0.25 = coord(1/4)
    
    Abstract
    Results from research in information retrieval have suggested that significant improvements in retrieval effectiveness can be obtained by combining results from multiple index representioms, query formulations, and search strategies. The inference net model of retrieval, which was designed from this point of view, treats information retrieval as an evidental reasoning process where multiple sources of evidence about document and query content are combined to estimate relevance probabilities. Uses a system based on this model to study the retrieval effectiveness benefits of combining these types of document and query information that are found in typical commercial databases and information services. The results indicate that substantial real benefits are possible
    Source
    Journal of the American Society for Information Science. 46(1995) no.4, S.272-283
  12. Croft, W.B.: Combining approaches to information retrieval (2000) 0.00
    0.004371658 = product of:
      0.017486632 = sum of:
        0.017486632 = weight(_text_:information in 6862) [ClassicSimilarity], result of:
          0.017486632 = score(doc=6862,freq=12.0), product of:
            0.06134496 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.034944877 = queryNorm
            0.2850541 = fieldWeight in 6862, product of:
              3.4641016 = tf(freq=12.0), with freq of:
                12.0 = termFreq=12.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.046875 = fieldNorm(doc=6862)
      0.25 = coord(1/4)
    
    Abstract
    The combination of different text representations and search strategies has become a standard technique for improving the effectiveness of information retrieval. Combination, for example, has been studied extensively in the TREC evaluations and is the basis of the "meta-search" engines used on the Web. This paper examines the development of this technique, including both experimental results and the retrieval models that have been proposed as formal frameworks for combination. We show that combining approaches for information retrieval can be modeled as combining the outputs of multiple classifiers based on one or more representations, and that this simple model can provide explanations for many of the experimental results. We also show that this view of combination is very similar to the inference net model, and that a new approach to retrieval based on language models supports combination and can be integrated with the inference net model
    Series
    The Kluwer international series on information retrieval; 7
    Source
    Advances in information retrieval: Recent research from the Center for Intelligent Information Retrieval. Ed.: W.B. Croft
  13. Turtle, H.; Croft, W.B.: Inference networks for document retrieval (1990) 0.00
    0.0042066295 = product of:
      0.016826518 = sum of:
        0.016826518 = weight(_text_:information in 1936) [ClassicSimilarity], result of:
          0.016826518 = score(doc=1936,freq=4.0), product of:
            0.06134496 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.034944877 = queryNorm
            0.27429342 = fieldWeight in 1936, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.078125 = fieldNorm(doc=1936)
      0.25 = coord(1/4)
    
    Footnote
    Wiederabgedruckt in: Readings in information retrieval. Ed.: K. Sparck Jones u. P. Willett. San Francisco: Morgan Kaufmann 1997. S.287-298
    Source
    Proceedings of the thirteenth international conference on research and development in information retrieval
  14. Callan, J.; Croft, W.B.; Broglio, J.: TREC and TIPSTER experiments with INQUERY (1995) 0.00
    0.0042066295 = product of:
      0.016826518 = sum of:
        0.016826518 = weight(_text_:information in 1944) [ClassicSimilarity], result of:
          0.016826518 = score(doc=1944,freq=4.0), product of:
            0.06134496 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.034944877 = queryNorm
            0.27429342 = fieldWeight in 1944, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.078125 = fieldNorm(doc=1944)
      0.25 = coord(1/4)
    
    Footnote
    Wiederabgedruckt in: Readings in information retrieval. Ed.: K. Sparck Jones u. P. Willett. San Francisco: Morgan Kaufmann 1997. S.436-439.
    Source
    Information processing and management. 31(1995) no.3, S.327-343
  15. Krovetz, R.; Croft, W.B.: Lexical ambiguity and information retrieval (1992) 0.00
    0.004164351 = product of:
      0.016657405 = sum of:
        0.016657405 = weight(_text_:information in 4028) [ClassicSimilarity], result of:
          0.016657405 = score(doc=4028,freq=8.0), product of:
            0.06134496 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.034944877 = queryNorm
            0.27153665 = fieldWeight in 4028, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.0546875 = fieldNorm(doc=4028)
      0.25 = coord(1/4)
    
    Abstract
    Reports on an analysis of lexical ambiguity in information retrieval text collections and on experiments to determine the utility of word meanings for separating relevant from nonrelevant documents. Results show that there is considerable ambiguity even in a specialised database. Word senses provide a significant separation between relevant and nonrelevant documents, but several factors contribute to determining whether disambiguation will make an improvement in performance such as: resolving lexical ambiguity was found to have little impact on retrieval effectiveness for documents that have many words in common with the query. Discusses other uses of word sense disambiguation in an information retrieval context
    Source
    ACM transactions on information systems. 10(1992) no.2, S.115-141
  16. Croft, W.B.; Thompson, R.H.: I3R: a new approach to the desing of document retrieval systems (1987) 0.00
    0.004164351 = product of:
      0.016657405 = sum of:
        0.016657405 = weight(_text_:information in 3898) [ClassicSimilarity], result of:
          0.016657405 = score(doc=3898,freq=2.0), product of:
            0.06134496 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.034944877 = queryNorm
            0.27153665 = fieldWeight in 3898, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.109375 = fieldNorm(doc=3898)
      0.25 = coord(1/4)
    
    Source
    Journal of the American Society for Information Science. 38(1987), S.389-404
  17. Luk, R.W.P.; Leong, H.V.; Dillon, T.S.; Chan, A.T.S.; Croft, W.B.; Allen, J.: ¬A survey in indexing and searching XML documents (2002) 0.00
    0.0039907596 = product of:
      0.015963038 = sum of:
        0.015963038 = weight(_text_:information in 460) [ClassicSimilarity], result of:
          0.015963038 = score(doc=460,freq=10.0), product of:
            0.06134496 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.034944877 = queryNorm
            0.2602176 = fieldWeight in 460, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.046875 = fieldNorm(doc=460)
      0.25 = coord(1/4)
    
    Abstract
    XML holds the promise to yield (1) a more precise search by providing additional information in the elements, (2) a better integrated search of documents from heterogeneous sources, (3) a powerful search paradigm using structural as well as content specifications, and (4) data and information exchange to share resources and to support cooperative search. We survey several indexing techniques for XML documents, grouping them into flatfile, semistructured, and structured indexing paradigms. Searching techniques and supporting techniques for searching are reviewed, including full text search and multistage search. Because searching XML documents can be very flexible, various search result presentations are discussed, as well as database and information retrieval system integration and XML query languages. We also survey various retrieval models, examining how they would be used or extended for retrieving XML documents. To conclude the article, we discuss various open issues that XML poses with respect to information retrieval and database research.
    Source
    Journal of the American Society for Information Science and technology. 53(2002) no.6, S.415-437
  18. Tavakoli, L.; Zamani, H.; Scholer, F.; Croft, W.B.; Sanderson, M.: Analyzing clarification in asynchronous information-seeking conversations (2022) 0.00
    0.0039907596 = product of:
      0.015963038 = sum of:
        0.015963038 = weight(_text_:information in 496) [ClassicSimilarity], result of:
          0.015963038 = score(doc=496,freq=10.0), product of:
            0.06134496 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.034944877 = queryNorm
            0.2602176 = fieldWeight in 496, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.046875 = fieldNorm(doc=496)
      0.25 = coord(1/4)
    
    Abstract
    This research analyzes human-generated clarification questions to provide insights into how they are used to disambiguate and provide a better understanding of information needs. A set of clarification questions is extracted from posts on the Stack Exchange platform. Novel taxonomy is defined for the annotation of the questions and their responses. We investigate the clarification questions in terms of whether they add any information to the post (the initial question posted by the asker) and the accepted answer, which is the answer chosen by the asker. After identifying, which clarification questions are more useful, we investigated the characteristics of these questions in terms of their types and patterns. Non-useful clarification questions are identified, and their patterns are compared with useful clarifications. Our analysis indicates that the most useful clarification questions have similar patterns, regardless of topic. This research contributes to an understanding of clarification in conversations and can provide insight for clarification dialogues in conversational search scenarios and for the possible system generation of clarification requests in information-seeking conversations.
    Source
    Journal of the Association for Information Science and Technology. 73(2022) no.3, S.449-471
  19. Liu, X.; Croft, W.B.: Statistical language modeling for information retrieval (2004) 0.00
    0.0039349417 = product of:
      0.015739767 = sum of:
        0.015739767 = weight(_text_:information in 4277) [ClassicSimilarity], result of:
          0.015739767 = score(doc=4277,freq=14.0), product of:
            0.06134496 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.034944877 = queryNorm
            0.256578 = fieldWeight in 4277, product of:
              3.7416575 = tf(freq=14.0), with freq of:
                14.0 = termFreq=14.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.0390625 = fieldNorm(doc=4277)
      0.25 = coord(1/4)
    
    Abstract
    This chapter reviews research and applications in statistical language modeling for information retrieval (IR), which has emerged within the past several years as a new probabilistic framework for describing information retrieval processes. Generally speaking, statistical language modeling, or more simply language modeling (LM), involves estimating a probability distribution that captures statistical regularities of natural language use. Applied to information retrieval, language modeling refers to the problem of estimating the likelihood that a query and a document could have been generated by the same language model, given the language model of the document either with or without a language model of the query. The roots of statistical language modeling date to the beginning of the twentieth century when Markov tried to model letter sequences in works of Russian literature (Manning & Schütze, 1999). Zipf (1929, 1932, 1949, 1965) studied the statistical properties of text and discovered that the frequency of works decays as a Power function of each works rank. However, it was Shannon's (1951) work that inspired later research in this area. In 1951, eager to explore the applications of his newly founded information theory to human language, Shannon used a prediction game involving n-grams to investigate the information content of English text. He evaluated n-gram models' performance by comparing their crossentropy an texts with the true entropy estimated using predictions made by human subjects. For many years, statistical language models have been used primarily for automatic speech recognition. Since 1980, when the first significant language model was proposed (Rosenfeld, 2000), statistical language modeling has become a fundamental component of speech recognition, machine translation, and spelling correction.
    Source
    Annual review of information science and technology. 39(2005), S.3-32
  20. Jing, Y.; Croft, W.B.: ¬An association thesaurus for information retrieval (199?) 0.00
    0.003606434 = product of:
      0.014425736 = sum of:
        0.014425736 = weight(_text_:information in 4494) [ClassicSimilarity], result of:
          0.014425736 = score(doc=4494,freq=6.0), product of:
            0.06134496 = queryWeight, product of:
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.034944877 = queryNorm
            0.23515764 = fieldWeight in 4494, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              1.7554779 = idf(docFreq=20772, maxDocs=44218)
              0.0546875 = fieldNorm(doc=4494)
      0.25 = coord(1/4)
    
    Abstract
    Although commonly used in both commercial and experimental information retrieval systems, thesauri have not demonstrated consistent benefits for retrieval performance, and it is difficult to construct a thesaurus automatically for large text databases. In this paper, an approach, called PhraseFinder, is proposed to construct collection-dependent association thesauri automatically using large full-text document collections. The association thesaurus can be accessed through natural language queries in INQUERY, an information retrieval system based on the probabilistic inference network. Experiments are conducted in INQUERY to evaluate different types of association thesauri, and thesauri constructed for a variety of collections