Search (3 results, page 1 of 1)

  • × author_ss:"Goh, A."
  1. Goh, A.; Hui, S.C.: TES: a text extraction system (1996) 0.03 
    0.03261434 = product of:
  0.06522868 = sum of:
    0.06522868 = sum of:
      0.015308296 = weight(_text_:a in 6599) [ClassicSimilarity], result of:
        0.015308296 = score(doc=6599,freq=16.0), product of:
          0.053105544 = queryWeight, product of:
            1.153047 = idf(docFreq=37942, maxDocs=44218)
            0.046056706 = queryNorm
          0.28826174 = fieldWeight in 6599, product of:
            4.0 = tf(freq=16.0), with freq of:
              16.0 = termFreq=16.0
            1.153047 = idf(docFreq=37942, maxDocs=44218)
            0.0625 = fieldNorm(doc=6599)
      0.04992038 = weight(_text_:22 in 6599) [ClassicSimilarity], result of:
        0.04992038 = score(doc=6599,freq=2.0), product of:
          0.16128273 = queryWeight, product of:
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.046056706 = queryNorm
          0.30952093 = fieldWeight in 6599, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            3.5018296 = idf(docFreq=3622, maxDocs=44218)
            0.0625 = fieldNorm(doc=6599)
  0.5 = coord(1/2)
    Abstract
    With the onset of the information explosion arising from digital libraries and access to a wealth of information through the Internet, the need to efficiently determine the relevance of a document becomes even more urgent. Describes a text extraction system (TES), which retrieves a set of sentences from a document to form an indicative abstract. Such an automated process enables information to be filtered more quickly. Discusses the combination of various text extraction techniques. Compares results with manually produced abstracts
    Date
    26. 2.1997 10:22:43
    Type
    a
  2. Goh, A.; Hui, S.C.; Chan, S.K.: ¬A text extraction system for news reports (1996) 0.00 
    0.0022374375 = product of:
  0.004474875 = sum of:
    0.004474875 = product of:
      0.00894975 = sum of:
        0.00894975 = weight(_text_:a in 6601) [ClassicSimilarity], result of:
          0.00894975 = score(doc=6601,freq=14.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.1685276 = fieldWeight in 6601, product of:
              3.7416575 = tf(freq=14.0), with freq of:
                14.0 = termFreq=14.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=6601)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    Abstract
    Describes the design and implementation of a text extraction tool, NEWS_EXT, which aztomatically produces summaries from news reports by extracting sentences to form indicative abstracts. Selection of sentences is based on sentence importance, measured by means of sentence scoring or simple linguistic analysis of sentence structure. Tests were conducted on 4 approaches for the functioning of the NEWS_EXT system; extraction by keyword frequency; extraction by title keywords; extraction by location; and extraction by indicative phrase. Reports results of a study to compare the results of the application of NEWS_EXT with manually produced extracts; using relevance as the criterion for effectiveness. 48 newspaper articles were assessed (The Straits Times, International Herald Tribune, Asian Wall Street Journal, and Financial Times). The evaluation was conducted in 2 stages: stage 1 involving abstracts produced manually by 2 human experts; stage 2 involving the generation of abstracts using NEWS_EXT. Results of each of the 4 approaches were compared with the human produced abstracts, where the title and location approaches were found to give the best results for both local and foreign news. Reports plans to refine and enhance NEWS_EXT and incorporate it as a module within a larger newspaper clipping system
    Type
    a
  3. Kok, Y.H.; Holaday, D.A.; Goh, A.; Holaday, D.A.: Using cluster analysis to determine the media agenda (1999) 0.00 
    0.0020296127 = product of:
  0.0040592253 = sum of:
    0.0040592253 = product of:
      0.008118451 = sum of:
        0.008118451 = weight(_text_:a in 728) [ClassicSimilarity], result of:
          0.008118451 = score(doc=728,freq=8.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.15287387 = fieldWeight in 728, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046875 = fieldNorm(doc=728)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    Abstract
    This paper describes a software tool that aids researchers in the study of agenda setting. Agenda setting theory claims that the mass media influences what the public thinks and talks about. The tool is used to cluster documents into topically coherent groupings that are to represent issues dominating press coverage. The documents are taken from the archives of online newspapers. In addition, the tool enables results to be visualised and displayed. Three methods were investigated for the purpose of clustering, of which the Group-Average-Linkage algorithm was chosen for the final testing. The choice of the clustering algorithm was predominantly made upon the quality of clusters produced. Comparisons between the computer-based results and a method involving human readers revealed comparable findings and potential usefulness of the software.
    Type
    a

Authors