Search (2 results, page 1 of 1)

  • × language_ss:"e"
  • × theme_ss:"Computerlinguistik"
  • × theme_ss:"Suchmaschinen"
  1. Nait-Baha, L.; Jackiewicz, A.; Djioua, B.; Laublet, P.: Query reformulation for information retrieval on the Web using the point of view methodology : preliminary results (2001) 0.01 
    0.007499164 = product of:
  0.029996656 = sum of:
    0.019452421 = weight(_text_:retrieval in 249) [ClassicSimilarity], result of:
      0.019452421 = score(doc=249,freq=2.0), product of:
        0.09700725 = queryWeight, product of:
          3.024915 = idf(docFreq=5836, maxDocs=44218)
          0.032069415 = queryNorm
        0.20052543 = fieldWeight in 249, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.024915 = idf(docFreq=5836, maxDocs=44218)
          0.046875 = fieldNorm(doc=249)
    0.010544236 = product of:
      0.021088472 = sum of:
        0.021088472 = weight(_text_:system in 249) [ClassicSimilarity], result of:
          0.021088472 = score(doc=249,freq=2.0), product of:
            0.10100432 = queryWeight, product of:
              3.1495528 = idf(docFreq=5152, maxDocs=44218)
              0.032069415 = queryNorm
            0.20878783 = fieldWeight in 249, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.1495528 = idf(docFreq=5152, maxDocs=44218)
              0.046875 = fieldNorm(doc=249)
      0.5 = coord(1/2)
  0.25 = coord(2/8)
    Abstract
    The work we are presenting is devoted to the information collected on the WWW. By the term collected we mean the whole process of retrieving, extracting and presenting results to the user. This research is part of the RAP (Research, Analyze, Propose) project in which we propose to combine two methods: (i) query reformulation using linguistic markers according to a given point of view; and (ii) text semantic analysis by means of contextual exploration results (Descles, 1991). The general project architecture describing the interactions between the users, the RAP system and the WWW search engines is presented in Nait-Baha et al. (1998). We will focus this paper on showing how we use linguistic markers to reformulate the queries according to a given point of view
  2. Radev, D.; Fan, W.; Qu, H.; Wu, H.; Grewal, A.: Probabilistic question answering on the Web (2005) 0.01 
    0.007499164 = product of:
  0.029996656 = sum of:
    0.019452421 = weight(_text_:retrieval in 3455) [ClassicSimilarity], result of:
      0.019452421 = score(doc=3455,freq=2.0), product of:
        0.09700725 = queryWeight, product of:
          3.024915 = idf(docFreq=5836, maxDocs=44218)
          0.032069415 = queryNorm
        0.20052543 = fieldWeight in 3455, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.024915 = idf(docFreq=5836, maxDocs=44218)
          0.046875 = fieldNorm(doc=3455)
    0.010544236 = product of:
      0.021088472 = sum of:
        0.021088472 = weight(_text_:system in 3455) [ClassicSimilarity], result of:
          0.021088472 = score(doc=3455,freq=2.0), product of:
            0.10100432 = queryWeight, product of:
              3.1495528 = idf(docFreq=5152, maxDocs=44218)
              0.032069415 = queryNorm
            0.20878783 = fieldWeight in 3455, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.1495528 = idf(docFreq=5152, maxDocs=44218)
              0.046875 = fieldNorm(doc=3455)
      0.5 = coord(1/2)
  0.25 = coord(2/8)
    Abstract
    Web-based search engines such as Google and NorthernLight return documents that are relevant to a user query, not answers to user questions. We have developed an architecture that augments existing search engines so that they support natural language question answering. The process entails five steps: query modulation, document retrieval, passage extraction, phrase extraction, and answer ranking. In this article, we describe some probabilistic approaches to the last three of these stages. We show how our techniques apply to a number of existing search engines, and we also present results contrasting three different methods for question answering. Our algorithm, probabilistic phrase reranking (PPR), uses proximity and question type features and achieves a total reciprocal document rank of .20 an the TREC8 corpus. Our techniques have been implemented as a Web-accessible system, called NSIR.

Authors

Themes