Search (3 results, page 1 of 1)

0.025035713 = product of:
  0.050071426 = sum of:
    0.031038022 = weight(_text_:data in 2421) [ClassicSimilarity], result of:
      0.031038022 = score(doc=2421,freq=2.0), product of:
        0.14807065 = queryWeight, product of:
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.046827413 = queryNorm
        0.2096163 = fieldWeight in 2421, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.046875 = fieldNorm(doc=2421)
    0.019033402 = product of:
      0.038066804 = sum of:
        0.038066804 = weight(_text_:22 in 2421) [ClassicSimilarity], result of:
          0.038066804 = score(doc=2421,freq=2.0), product of:
            0.16398162 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.046827413 = queryNorm
            0.23214069 = fieldWeight in 2421, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.046875 = fieldNorm(doc=2421)
      0.5 = coord(1/2)
  0.5 = coord(2/4)

Abstract

Graph-based ranking algorithms have recently been proposed for single document summarizations and such algorithms evaluate the importance of a sentence by making use of the relationships between sentences in the document in a recursive way. In this paper, we investigate using other related or relevant documents to improve summarization of one single document based on the graph-based ranking algorithm. In addition to the within-document relationships between sentences in the specified document, the cross-document relationships between sentences in different documents are also taken into account in the proposed approach. We evaluate the performance of the proposed approach on DUC 2002 data with the ROUGE metric and results demonstrate that the cross-document relationships between sentences in different but related documents can significantly improve the performance of single document summarization.

Source

Research and advanced technology for digital libraries : 10th European conference, proceedings / ECDL 2006, Alicante, Spain, September 17 - 22, 2006

0.006466255 = product of:
  0.02586502 = sum of:
    0.02586502 = weight(_text_:data in 2362) [ClassicSimilarity], result of:
      0.02586502 = score(doc=2362,freq=2.0), product of:
        0.14807065 = queryWeight, product of:
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.046827413 = queryNorm
        0.17468026 = fieldWeight in 2362, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.1620505 = idf(docFreq=5088, maxDocs=44218)
          0.0390625 = fieldNorm(doc=2362)
  0.25 = coord(1/4)

Abstract

Many writers of structured abstracts spend a good deal of time revising and polishing their texts - but is it worth it? Do readers notice the difference? In this paper we report three studies of readers using rating scales to judge (electronically) the clarity of an original and a revised abstract, both as a whole and in its constituent parts. In Study 1, with approximately 250 academics and research workers, we found some significant differences in favor of the revised abstract, but in Study 2, with approximately 210 information scientists, we found no significant effects. Pooling the data from Studies 1 and 2, however, in Study 3, led to significant differences at a higher probability level between the perception of the original and revised abstract as a whole and between the same components as found in Study 1. These results thus indicate that the revised abstract as a whole, as well as certain specific components of it, were judged significantly clearer than the original one. In short, the results of these experiments show that readers can and do perceive differences between original and revised texts - sometimes - and that therefore these efforts are worth the time and effort.

0.005299047 = product of:
  0.021196188 = sum of:
    0.021196188 = product of:
      0.042392377 = sum of:
        0.042392377 = weight(_text_:processing in 5049) [ClassicSimilarity], result of:
          0.042392377 = score(doc=5049,freq=2.0), product of:
            0.18956426 = queryWeight, product of:
              4.048147 = idf(docFreq=2097, maxDocs=44218)
              0.046827413 = queryNorm
            0.22363065 = fieldWeight in 5049, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              4.048147 = idf(docFreq=2097, maxDocs=44218)
              0.0390625 = fieldNorm(doc=5049)
      0.5 = coord(1/2)
  0.25 = coord(1/4)

Abstract

Based on the salient features of the documents, automatic text summarization systems extract the key sentences from source documents. This process supports the users in evaluating the relevance of the extracted documents returned by information retrieval systems. Because of this tool, efficient filtering can be achieved. Indirectly, these systems help to resolve the problem of information overloading. Many automatic text summarization systems have been implemented for use with different languages. It has been established that the grammatical and lexical differences between languages have a significant effect on text processing. However, the impact of the language differences on the automatic text summarization systems has not yet been investigated. The authors provide an impact analysis of language difference on automatic text summarization. It includes the effect on the extraction processes, the scoring mechanisms, the performance, and the matching of the extracted sentences, using the parallel corpus in English and Chinese as the tested object. The analysis results provide a greater understanding of language differences and promote the future development of more advanced text summarization techniques.