Search (1 results, page 1 of 1)

  • × author_ss:"Anizi, M."
  • × theme_ss:"Computerlinguistik"
  1. Anizi, M.; Dichy, J.: Improving information retrieval in Arabic through a multi-agent approach and a rich lexical resource (2011) 0.00
    9.7151217E-4 = product of:
      0.01117239 = sum of:
        0.0039282576 = product of:
          0.007856515 = sum of:
            0.007856515 = weight(_text_:1 in 4738) [ClassicSimilarity], result of:
              0.007856515 = score(doc=4738,freq=2.0), product of:
                0.057894554 = queryWeight, product of:
                  2.4565027 = idf(docFreq=10304, maxDocs=44218)
                  0.023567878 = queryNorm
                0.13570388 = fieldWeight in 4738, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  2.4565027 = idf(docFreq=10304, maxDocs=44218)
                  0.0390625 = fieldNorm(doc=4738)
          0.5 = coord(1/2)
        0.0072441325 = product of:
          0.014488265 = sum of:
            0.014488265 = weight(_text_:international in 4738) [ClassicSimilarity], result of:
              0.014488265 = score(doc=4738,freq=2.0), product of:
                0.078619614 = queryWeight, product of:
                  3.33588 = idf(docFreq=4276, maxDocs=44218)
                  0.023567878 = queryNorm
                0.18428308 = fieldWeight in 4738, product of:
                  1.4142135 = tf(freq=2.0), with freq of:
                    2.0 = termFreq=2.0
                  3.33588 = idf(docFreq=4276, maxDocs=44218)
                  0.0390625 = fieldNorm(doc=4738)
          0.5 = coord(1/2)
      0.08695652 = coord(2/23)
    
    Abstract
    This paper addresses the optimization of information retrieval in Arabic. The results derived from the expanding development of sites in Arabic are often spectacular. Nevertheless, several observations indicate that the responses remain disappointing, particularly upon comparing users' requests and quality of responses. One of the problems encountered by users is the loss of time when navigating between different URLs to find adequate responses. This, in many cases, is due to the absence of forms morphologically related to the research keyword. Such problems can be approached through a morphological analyzer drawing on the DIINAR.1 morpho-lexical resource. A second problem concerns the formulation of the query, which may prove ambiguous, as in everyday language. We then focus on contextual disambiguation based on a rich lexical resource that includes collocations and set expressions. The overall scheme of such a resource will only be hinted at here. Our approach leads to the elaboration of a multi-agent system, motivated by a need to solve problems encountered when using conventional methods of analysis, and to improve the results of queries thanks to a better collaboration between different levels of analysis. We suggest resorting to four agents: morphological, morpho-lexical, contextualization, and an interface agent. These agents 'negotiate' and 'cooperate' throughout the analysis process, starting from the submission of the initial query, and going on until an adequate query is obtained.
    Content
    Beitrag innerhalb einer Special Section: Knowledge Organization, Competitive Intelligence, and Information Systems - Papers from 4th International Conference on "Information Systems & Economic Intelligence," February 17-19th, 2011. Marrakech - Morocco.