Search (21 results, page 1 of 2)

  • × language_ss:"e"
  • × theme_ss:"Automatisches Abstracting"
  • × year_i:[1990 TO 2000}
  1. Paice, C.D.: Automatic abstracting (1994) 0.09 
    0.08912055 = product of:
  0.1782411 = sum of:
    0.01841403 = weight(_text_:for in 917) [ClassicSimilarity], result of:
      0.01841403 = score(doc=917,freq=2.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.20744109 = fieldWeight in 917, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.078125 = fieldNorm(doc=917)
    0.15982707 = weight(_text_:computing in 917) [ClassicSimilarity], result of:
      0.15982707 = score(doc=917,freq=2.0), product of:
        0.26151994 = queryWeight, product of:
          5.5314693 = idf(docFreq=475, maxDocs=44218)
          0.047278564 = queryNorm
        0.6111468 = fieldWeight in 917, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          5.5314693 = idf(docFreq=475, maxDocs=44218)
          0.078125 = fieldNorm(doc=917)
  0.5 = coord(2/4)
    Abstract
    The final report of the 2nd British Library abstracting project (the BLAB project), 1990-1992, which was carried out partly at the Computing Department of Lancaster University, and partly at the Centre for Computational Linguistics, UMIST. This project built on the results of the first project, of 1985-1987, to build a system designed create abstracts automatically from given texts
  2. Robin, J.; McKeown, K.: Empirically designing and evaluating a new revision-based model for summary generation (1996) 0.02 
    0.023227734 = product of:
  0.04645547 = sum of:
    0.020833097 = weight(_text_:for in 6751) [ClassicSimilarity], result of:
      0.020833097 = score(doc=6751,freq=4.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.23469281 = fieldWeight in 6751, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.0625 = fieldNorm(doc=6751)
    0.025622372 = product of:
      0.051244743 = sum of:
        0.051244743 = weight(_text_:22 in 6751) [ClassicSimilarity], result of:
          0.051244743 = score(doc=6751,freq=2.0), product of:
            0.16556148 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.047278564 = queryNorm
            0.30952093 = fieldWeight in 6751, 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=6751)
      0.5 = coord(1/2)
  0.5 = coord(2/4)
    Abstract
    Presents a system for summarizing quantitative data in natural language, focusing on the use of a corpus of basketball game summaries, drawn from online news services, to empirically shape the system design and to evaluate the approach. Initial corpus analysis revealed characteristics of textual summaries that challenge the capabilities of current language generation systems. A revision based corpus analysis was used to identify and encode the revision rules of the system. Presents a quantitative evaluation, using several test corpora, to measure the robustness of the new revision based model
    Date
    6. 3.1997 16:22:15
  3. Goh, A.; Hui, S.C.: TES: a text extraction system (1996) 0.02 
    0.020176798 = product of:
  0.040353596 = sum of:
    0.014731225 = weight(_text_:for in 6599) [ClassicSimilarity], result of:
      0.014731225 = score(doc=6599,freq=2.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.16595288 = fieldWeight in 6599, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.0625 = fieldNorm(doc=6599)
    0.025622372 = product of:
      0.051244743 = sum of:
        0.051244743 = weight(_text_:22 in 6599) [ClassicSimilarity], result of:
          0.051244743 = score(doc=6599,freq=2.0), product of:
            0.16556148 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.047278564 = 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)
  0.5 = coord(2/4)
    Date
    26. 2.1997 10:22:43
    Source
    Microcomputers for information management. 13(1996) no.1, S.41-55
  4. Liu, J.; Wu, Y.; Zhou, L.: ¬A hybrid method for abstracting newspaper articles (1999) 0.01 
    0.008235005 = product of:
  0.03294002 = sum of:
    0.03294002 = weight(_text_:for in 4059) [ClassicSimilarity], result of:
      0.03294002 = score(doc=4059,freq=10.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.37108192 = fieldWeight in 4059, product of:
          3.1622777 = tf(freq=10.0), with freq of:
            10.0 = termFreq=10.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.0625 = fieldNorm(doc=4059)
  0.25 = coord(1/4)
    Abstract
    This paper introduces a hybrid method for abstracting Chinese text. It integrates the statistical approach with language understanding. Some linguistics heuristics and segmentation are also incorporated into the abstracting process. The prototype system is of a multipurpose type catering for various users with different reqirements. Initial responses show that the proposed method contributes much to the flexibility and accuracy of the automatic Chinese abstracting system. In practice, the present work provides a path to developing an intelligent Chinese system for automating the information
    Source
    Journal of the American Society for Information Science. 50(1999) no.13, S.1234-1245
  5. McKeown, K.; Robin, J.; Kukich, K.: Generating concise natural language summaries (1995) 0.01 
    0.00797351 = product of:
  0.03189404 = sum of:
    0.03189404 = weight(_text_:for in 2932) [ClassicSimilarity], result of:
      0.03189404 = score(doc=2932,freq=6.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.35929856 = fieldWeight in 2932, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.078125 = fieldNorm(doc=2932)
  0.25 = coord(1/4)
    Abstract
    Description of the problems for summary generation, the applications developed (for basket ball games - STREAK and for telephone network planning activity - PLANDOC), the linguistic constructions that the systems use to convey information concisely and the textual constraints that determine what information gets included
  6. Jones, P.A.; Bradbeer, P.V.G.: Discovery of optimal weights in a concept selection system (1996) 0.01 
    0.006405593 = product of:
  0.025622372 = sum of:
    0.025622372 = product of:
      0.051244743 = sum of:
        0.051244743 = weight(_text_:22 in 6974) [ClassicSimilarity], result of:
          0.051244743 = score(doc=6974,freq=2.0), product of:
            0.16556148 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.047278564 = queryNorm
            0.30952093 = fieldWeight in 6974, 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=6974)
      0.5 = coord(1/2)
  0.25 = coord(1/4)
    Source
    Information retrieval: new systems and current research. Proceedings of the 16th Research Colloquium of the British Computer Society Information Retrieval Specialist Group, Drymen, Scotland, 22-23 Mar 94. Ed.: R. Leon
  7. Craven, T.C.: ¬A phrase flipper for the assistance of writers of abstracts and other text (1995) 0.01 
    0.0063788076 = product of:
  0.02551523 = sum of:
    0.02551523 = weight(_text_:for in 4897) [ClassicSimilarity], result of:
      0.02551523 = score(doc=4897,freq=6.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.28743884 = fieldWeight in 4897, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.0625 = fieldNorm(doc=4897)
  0.25 = coord(1/4)
    Abstract
    Describes computerized tools for computer assisted abstracting. FlipPhr is a Microsoft Windows application program that rearranges (flips) phrases or other expressions in accordance with rules in a grammar. The flipping may be invoked with a single keystroke from within various Windows application programs that allow cutting and pasting of text. The user may modify the grammar to provide for different kinds of flipping
  8. Salton, G.: Automatic text structuring and summarization (1997) 0.01 
    0.0055814567 = product of:
  0.022325827 = sum of:
    0.022325827 = weight(_text_:for in 145) [ClassicSimilarity], result of:
      0.022325827 = score(doc=145,freq=6.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.25150898 = fieldWeight in 145, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.0546875 = fieldNorm(doc=145)
  0.25 = coord(1/4)
    Abstract
    Applies the ideas from the automatic link generation research to automatic text summarisation. Using techniques for inter-document link generation, generates intra-document links between passages of a document. Based on the intra-document linkage pattern of a text, characterises the structure of the text. Applies the knowledge of text structure to do automatic text summarisation by passage extraction. Evaluates a set of 50 summaries generated using these techniques by comparing the to paragraph extracts constructed by humans. The automatic summarisation methods perform well, especially in view of the fact that the summaries generates by 2 humans for the same article are surprisingly dissimilar
    Footnote
    Contribution to a special issue on methods and tools for the automatic construction of hypertext
  9. Craven, T.C.: ¬A computer-aided abstracting tool kit (1993) 0.01 
    0.0052082743 = product of:
  0.020833097 = sum of:
    0.020833097 = weight(_text_:for in 6506) [ClassicSimilarity], result of:
      0.020833097 = score(doc=6506,freq=4.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.23469281 = fieldWeight in 6506, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.0625 = fieldNorm(doc=6506)
  0.25 = coord(1/4)
    Abstract
    Describes the abstracting assistance features being prototyped in the TEXNET text network management system. Sentence weighting methods include: weithing negatively or positively on the stems in a selected passage; weighting on general lists of cue words, adjusting weights of selected segments; and weighting of occurrence of frequent stems. The user may adjust a number of parameters: the minimum strength of extracts; the threshold for frequent word/stems and the amount sentence weight is to be adjusted for each weighting type
  10. Moens, M.-F.; Uyttendaele, C.; Dumotier, J.: Abstracting of legal cases : the potential of clustering based on the selection of representative objects (1999) 0.00 
    0.004784106 = product of:
  0.019136423 = sum of:
    0.019136423 = weight(_text_:for in 2944) [ClassicSimilarity], result of:
      0.019136423 = score(doc=2944,freq=6.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.21557912 = fieldWeight in 2944, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.046875 = fieldNorm(doc=2944)
  0.25 = coord(1/4)
    Abstract
    The SALOMON project automatically summarizes Belgian criminal cases in order to improve access to the large number of existing and future court decisions. SALOMON extracts text units from the case text to form a case summary. Such a case summary facilitates the rapid determination of the relevance of the case or may be employed in text search. an important part of the research concerns the development of techniques for automatic recognition of representative text paragraphs (or sentences) in texts of unrestricted domains. these techniques are employed to eliminate redundant material in the case texts, and to identify informative text paragraphs which are relevant to include in the case summary. An evaluation of a test set of 700 criminal cases demonstrates that the algorithms have an application potential for automatic indexing, abstracting, and text linkage
    Source
    Journal of the American Society for Information Science. 50(1999) no.2, S.151-161
  11. Goh, A.; Hui, S.C.; Chan, S.K.: ¬A text extraction system for news reports (1996) 0.00 
    0.0046035075 = product of:
  0.01841403 = sum of:
    0.01841403 = weight(_text_:for in 6601) [ClassicSimilarity], result of:
      0.01841403 = score(doc=6601,freq=8.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.20744109 = fieldWeight in 6601, product of:
          2.828427 = tf(freq=8.0), with freq of:
            8.0 = termFreq=8.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.0390625 = fieldNorm(doc=6601)
  0.25 = coord(1/4)
    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
  12. Craven, T.C.: ¬An experiment in the use of tools for computer-assisted abstracting (1996) 0.00 
    0.0039062058 = product of:
  0.015624823 = sum of:
    0.015624823 = weight(_text_:for in 7426) [ClassicSimilarity], result of:
      0.015624823 = score(doc=7426,freq=4.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.17601961 = fieldWeight in 7426, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.046875 = fieldNorm(doc=7426)
  0.25 = coord(1/4)
    Source
    Global complexity: information, chaos and control. Proceedings of the 59th Annual Meeting of the American Society for Information Science, ASIS'96, Baltimore, Maryland, 21-24 Oct 1996. Ed.: S. Hardin
  13. Moens, M.-F.; Uyttendaele, C.: Automatic text structuring and categorization as a first step in summarizing legal cases (1997) 0.00 
    0.0039062058 = product of:
  0.015624823 = sum of:
    0.015624823 = weight(_text_:for in 2256) [ClassicSimilarity], result of:
      0.015624823 = score(doc=2256,freq=4.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.17601961 = fieldWeight in 2256, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.046875 = fieldNorm(doc=2256)
  0.25 = coord(1/4)
    Abstract
    The SALOMON system automatically summarizes Belgian criminal cases in order to improve access to the large number of existing and future court decisions. SALOMON extracts relevant text units from the case text to form a case summary. Such a case profile facilitates the rapid determination of the relevance of the case or may be employed in text search. In a first important abstracting step SALOMON performs an initial categorization of legal criminal cases and structures the case text into separate legally relevant and irrelevant components. A text grammar represented as a semantic network is used to automatically determine the category of the case and its components. Extracts from the case general data and identifies text portions relevant for further abstracting. Prior knowledge of the text structure and its indicative cues may support automatic abstracting. A text grammar is a promising form for representing the knowledge involved
  14. Brandow, R.; Mitze, K.; Rau, L.F.: Automatic condensation of electronic publications by sentence selection (1995) 0.00 
    0.0036828062 = product of:
  0.014731225 = sum of:
    0.014731225 = weight(_text_:for in 2929) [ClassicSimilarity], result of:
      0.014731225 = score(doc=2929,freq=2.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.16595288 = fieldWeight in 2929, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.0625 = fieldNorm(doc=2929)
  0.25 = coord(1/4)
    Abstract
    Description of a system that performs domain-independent automatic condensation of news from a large commercial news service encompassing 41 different publications. This system was evaluated against a system that condensed the same articles using only the first portions of the texts (the löead), up to the target length of the summaries. 3 lengths of articles were evaluated for 250 documents by both systems, totalling 1.500 suitability judgements in all. The lead-based summaries outperformed the 'intelligent' summaries significantly, achieving acceptability ratings of over 90%, compared to 74,7%
  15. Johnson, F.: Automatic abstracting research (1995) 0.00 
    0.0036828062 = product of:
  0.014731225 = sum of:
    0.014731225 = weight(_text_:for in 3847) [ClassicSimilarity], result of:
      0.014731225 = score(doc=3847,freq=2.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.16595288 = fieldWeight in 3847, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.0625 = fieldNorm(doc=3847)
  0.25 = coord(1/4)
    Abstract
    Discusses the attraction for researchers of the prospect of automatically generating abstracts but notes that the promise of superseding the human effort has yet to be realized. Notes ways in which progress in automatic abstracting research may come about and suggests a shift in the aim from reproducing the conventional benefits of abstracts to accentuating the advantages to users of the computerized representation of information in large textual databases
  16. Summarising software for publishing (1996) 0.00 
    0.0036828062 = product of:
  0.014731225 = sum of:
    0.014731225 = weight(_text_:for in 5121) [ClassicSimilarity], result of:
      0.014731225 = score(doc=5121,freq=2.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.16595288 = fieldWeight in 5121, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.0625 = fieldNorm(doc=5121)
  0.25 = coord(1/4)
  17. Ahmad, K.: Text summarisation : the role of lexical cohesion analysis (1995) 0.00 
    0.0036828062 = product of:
  0.014731225 = sum of:
    0.014731225 = weight(_text_:for in 5795) [ClassicSimilarity], result of:
      0.014731225 = score(doc=5795,freq=2.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.16595288 = fieldWeight in 5795, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.0625 = fieldNorm(doc=5795)
  0.25 = coord(1/4)
    Abstract
    The work in automatic text summary focuses mainly on computational models of texts. The artificial intelligence related work in text summary deals mainly with narrative texts such as newspaper reports and stories. Presents a study on the summary of non-narrative texts such as those in scientific and technical communication. Discusses syntactic cohesion; lexical cohesion; complex lexical repetition; simple and complex paraphrase; bonds and links; and Tele-pattan; an architecture for cohesion based text analysis and summarisation system working on SGML
  18. Endres-Niggemeyer, B.; Neugebauer, E.: Professional summarizing : no cognitive simulation without observation (1998) 0.00 
    0.0036828062 = product of:
  0.014731225 = sum of:
    0.014731225 = weight(_text_:for in 3243) [ClassicSimilarity], result of:
      0.014731225 = score(doc=3243,freq=2.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.16595288 = fieldWeight in 3243, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.0625 = fieldNorm(doc=3243)
  0.25 = coord(1/4)
    Source
    Journal of the American Society for Information Science. 49(1998) no.6, S.486-506
  19. Uyttendaele, C.; Moens, M.-F.; Dumortier, J.: SALOMON: automatic abstracting of legal cases for effective access to court decisions (1998) 0.00 
    0.0032224553 = product of:
  0.012889821 = sum of:
    0.012889821 = weight(_text_:for in 495) [ClassicSimilarity], result of:
      0.012889821 = score(doc=495,freq=2.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.14520876 = fieldWeight in 495, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.0546875 = fieldNorm(doc=495)
  0.25 = coord(1/4)
  20. Maybury, M.T.: Generating summaries from event data (1995) 0.00 
    0.0027621046 = product of:
  0.0110484185 = sum of:
    0.0110484185 = weight(_text_:for in 2349) [ClassicSimilarity], result of:
      0.0110484185 = score(doc=2349,freq=2.0), product of:
        0.08876751 = queryWeight, product of:
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.047278564 = queryNorm
        0.12446466 = fieldWeight in 2349, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.8775425 = idf(docFreq=18385, maxDocs=44218)
          0.046875 = fieldNorm(doc=2349)
  0.25 = coord(1/4)
    Abstract
    Summarization entails analysis of source material, selection of key information, condensation of this, and generation of a compct summary form. While there habe been many investigations into the automatic summarization of text, relatively little attention has been given to the summarization of information from structured information sources such as data of knowledge bases, despite this being a desirable capability for a number of application areas including report generation from databases (e.g. weather, financial, medical) and simulation (e.g. military, manufacturing, aconomic). After a brief introduction indicating the main elements of summarization and referring to some illustrative approaches to it, considers pecific issues in the generation of text summaries of event data, describes a system, SumGen, which selects key information from an event database by reasoning about event frequencies, frequencies of relations between events, and domain specific importance measures. Describes how Sum Gen then aggregates similar information and plans a summary presentations tailored to stereotypical users

Authors

Types

Themes

Subjects