Number of found records: 30
|
BOGURAEV, Branimir K.; NEFF, Mary S. |
|
Discourse Segmentation in Aid of Document Summarization |
|
PDF |
|
This paper describes work to enhance a sentence based summarizer with notions of salience, dynamically adjustable summary size, discourse segmentation, and awareness of topic shifts. Our experiments study strategies to diversify the application of a baseline summarizer, by making it aware of finer-grained 'aboutness', capable of discerning changes of topic, and sensitive to longer-than-usual documents. Evaluated against the corpus used in the development of the baseline summarizer, summaries derived either by means of segmentation analysis alone, or by a mix of strategies for combining salience calculation and topic shift detection, are shown to be of comparable, and under certain conditions even better, quality. We describe the summarization and segmentation procedures, outline a number of strategies for mixing the two, evaluate the overall impact of discourse segmentation, and suggest an interface design capable of using the notion of topic shifts to contextualize a summary and facilitate the mediation between it and the full document source (AU) |
|
baseline summarizer; segmentation analysis |
Assessment |
|
|
|
|
CRAVEN, Timothy C. |
|
Abstracts produced using computer assistance |
|
Journal of the American Society for Information Science, 2000, vol. 51, n. 8, pp.745-756. |
|
On line (09/05/2005) |
|
Experimental subjects wrote abstracts of articles using a simplified version of the TEXNET abstracting assistance software. In addition to the full text, subjects were presented with either keywords or phrases extracted automatically. The resulting abstracts, and the time taken, were recorded automatically, some additional information was gathered by oral questionnaire. Selected abstracts produced were evaluated on various criteria by independent raters. Results showed considerable variation among subjects, but 37 per cent found the keywords or phrases 'quite' or 'very' useful in writing their abstracts. Statistical analysis failed to support several hypothesised relations: phrases were not viewed as significantly more helpful than keywords; and abstracting experience did not correlate with originality of wording, approximation of the author abstract, or greater conciseness. Requiring further study are some unanticipated strong correlations including the following: Windows experience and writing an abstract like the author's; experience reading abstracts and thinking one had written a good abstract; gender and abstract length; gender and use of words and phrases from the original text. Results suggest possible modifications to the TEXNET software. (AU) |
|
Automatic text analysis; Computer assisted abstracting; Software; TEXNET |
Assessment |
|
|
|
|
CRAVEN, Timothy C. |
|
A computer-aided abstracting tool kit |
|
Canadian Journal of Information and Library Science,1993, vol.18, n.2, pp.20-31. |
|
PDF |
|
Describes the abstracting assistance features being prototyped in the TEXNET text network management system. Sentence weighting methods include: weighting negatively or positively on the stems in a selected passage; weighting on general lists of cue words, adjusting weights of selected segments; and weighting on occurrence of frequent stems. The user may adjust a number of parameters: the minimum strength of extracts; the threshold fro frequent word/stems and the amount sentence weight is to be adjusted for each weighting type. (AU) |
|
Automatic text analysis; Computer assisted abstracting; Weighting; TEXNET |
Assessment |
|
|
|
|
FURUTA, Richard; QUINT, Vincent; ANDRÉ, Jacques |
|
Interactively editing structured documents. |
|
Electronic publishing, 1988, vol. 1, n.1, pp. 19-44 |
|
PDF |
|
Document preparation systems that are oriented to an author's preparation of printed material must permit the flexible specification, modification, and reuse of the contents of the document. Interactive document preparation systems commonly have incorporated simple representations-an unconstrained linear list of document objects in the 'What You See Is What You Get' (WYSIWYG) systems. Recent research projects have been directed at the interactive manipulation of richer tree-oriented representations in which object relationships are constrained through grammatical specification. The advantage of such representations is the increased flexibility that they provide in the reusability of the document and its components and the more powerful user commands that they permit. We report on the experience gained from the design of two such systems. Although the two systems were designed independently of each other, a common set of issues, representations, and techniques has been identified. An important component of these projects has been to examine the WYSIWYG user interface, retaining the naturalness of their user interface but eliminating their dependencies on the physical-page representation. Aspects of the design of such systems remain open for further research. We describe these open research problems and indicate some of the further gains that may be achievable through investigation of these document representations. (AU) |
|
Document preparation systems; Structured documents; Grammatically-defined generic document structures; User interfaces Design experience |
Assessment |
|
|
|
|
