Search (3 results, page 1 of 1)

  • × year_i:[2000 TO 2010}
  • × author_ss:"Allan, J."
  1. Papka, R.; Allan, J.: Topic detection and tracking : event clustering as a basis for first story detection (2000) 0.00 
    0.0012555057 = product of:
  0.00878854 = sum of:
    0.00878854 = product of:
      0.0439427 = sum of:
        0.0439427 = weight(_text_:retrieval in 34) [ClassicSimilarity], result of:
          0.0439427 = score(doc=34,freq=8.0), product of:
            0.109568894 = queryWeight, product of:
              3.024915 = idf(docFreq=5836, maxDocs=44218)
              0.03622214 = queryNorm
            0.40105087 = fieldWeight in 34, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              3.024915 = idf(docFreq=5836, maxDocs=44218)
              0.046875 = fieldNorm(doc=34)
      0.2 = coord(1/5)
  0.14285715 = coord(1/7)
    Abstract
    Topic Detection and Tracking (TDT) is a new research area that investigates the organization of information by event rather than by subject. In this paper, we provide an overview of the TDT research program from its inception to the third phrase that is now underway. We also discuss our approach to two of the TDT problems in detail. For event clustering (Detection), we show that classic Information Retrieval clustering techniques can be modified slightly to provide effective solutions. For first story detection, we show that similar methods provide satisfactory results, although substantial work remains. In both cases, we explore solutions that model the temporal relationship between news stories. We also investigate the use of phrase extraction to capture the who, what, when, and where contained in news
    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
  2. Allan, J.; Croft, W.B.; Callan, J.: ¬The University of Massachusetts and a dozen TRECs (2005) 0.00 
    0.0012555057 = product of:
  0.00878854 = sum of:
    0.00878854 = product of:
      0.0439427 = sum of:
        0.0439427 = weight(_text_:retrieval in 5086) [ClassicSimilarity], result of:
          0.0439427 = score(doc=5086,freq=2.0), product of:
            0.109568894 = queryWeight, product of:
              3.024915 = idf(docFreq=5836, maxDocs=44218)
              0.03622214 = queryNorm
            0.40105087 = fieldWeight in 5086, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.024915 = idf(docFreq=5836, maxDocs=44218)
              0.09375 = fieldNorm(doc=5086)
      0.2 = coord(1/5)
  0.14285715 = coord(1/7)
    Source
    TREC: experiment and evaluation in information retrieval. Ed.: E.M. Voorhees, u. D.K. Harman
  3. Kumaran, G.; Allan, J.: Adapting information retrieval systems to user queries (2008) 0.00 
    0.0010873 = product of:
  0.0076110996 = sum of:
    0.0076110996 = product of:
      0.0380555 = sum of:
        0.0380555 = weight(_text_:retrieval in 2075) [ClassicSimilarity], result of:
          0.0380555 = score(doc=2075,freq=6.0), product of:
            0.109568894 = queryWeight, product of:
              3.024915 = idf(docFreq=5836, maxDocs=44218)
              0.03622214 = queryNorm
            0.34732026 = fieldWeight in 2075, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              3.024915 = idf(docFreq=5836, maxDocs=44218)
              0.046875 = fieldNorm(doc=2075)
      0.2 = coord(1/5)
  0.14285715 = coord(1/7)
    Abstract
    Users enter queries that are short as well as long. The aim of this work is to evaluate techniques that can enable information retrieval (IR) systems to automatically adapt to perform better on such queries. By adaptation we refer to (1) modifications to the queries via user interaction, and (2) detecting that the original query is not a good candidate for modification. We show that the former has the potential to improve mean average precision (MAP) of long and short queries by 40% and 30% respectively, and that simple user interaction can help towards this goal. We observed that after inspecting the options presented to them, users frequently did not select any. We present techniques in this paper to determine beforehand the utility of user interaction to avoid this waste of time and effort. We show that our techniques can provide IR systems with the ability to detect and avoid interaction for unpromising queries without a significant drop in overall performance.
    Footnote
    Beitrag in einem Themenheft "Adaptive information retrieval"

Authors