BibSonomy publications for /user/diego_ma/COMP448Wed Mar 19 05:51:36 CET 2008Proc. ACM conference on Information and Knowledge Management (CIKM)8 pagesTraining a Selection Function for Extraction1999COMP448 summarisation In this paper we compare performance of several heuristics in generating informative generic/query-oriented extracts for newspaper articles in order to learn how topic prominence affects the performance of each heuristic. We study how different query types can affect the performance of each heuristic and discuss the possibility of using machine learning algorithms to automatically learn good combination functions to combine several heuristics. We also briefly describe the design, implementation, and performance of a multilingual text summarization system SUMMARIST.Wed Mar 19 05:50:38 CET 2008IBM Journal159-165The Automatic Creation of Literature Abstracts21958summarisation COMP448 Excerpts of technical papers and magazine articles that serve the purpose of conventional abstracts have been created entirely by automatic means. In the exploratory research described, the complete text of an article in machine-readable form is scanned by an IBM 704 data-processing machine and analyzed in accordance with a standard program. Statistical information derived from word frequency and distribution is used by the machine to compute a relative measure of significance, first for individual words and then for sentences. Sentences scoring highest in significance are extracted and printed out to become the ``auto-abstract.''Wed Mar 12 04:43:46 CET 2008Proc. ACL workshop on Text Summarization Branches Out10ROUGE: A Package for Automatic Evaluation of summaries2004evaluation COMP448 summarisation ROUGE stands for Recall-Oriented Understudy for Gisting Evaluation. It includes measures to automatically determine the quality of a summary by comparing it to other (ideal) summaries created by humans. The measures count the number of overlapping units such as n-gram, word sequences, and word pairs between the computer-generated summary to be evaluated and the ideal summaries created by humans. This paper introduces four different ROUGE measures: ROUGE-N, ROUGE-L, ROUGE-W, and ROUGE-S included in the ROUGE summarization evaluation package and their evaluations. Three of them have been used in the Document Understanding Conference (DUC) 2004, a large-scale sum- marization evaluation sponsored by NIST.Wed Mar 12 04:42:41 CET 2008Proc. HLT-NAACL8 pagesAutomatic Evaluation of Summaries Using N-Gram Co-occurrence Statistics2003COMP448 evaluation summarisation Following the recent adoption by the machine translation community of automatic evaluation using the BLEU/NIST scoring process, we conduct an in-depth study of a similar idea for evaluating summaries. The results show that automatic evaluation using unigram co-occurrences between summary pairs correlates surprising well with human evaluations, based on various statistical metrics; while direct application of the BLEU evaluation procedure does not always give good results.Tue Mar 04 08:02:57 CET 2008Information Processing \& Management1171-186Constructing Literature Abstracts by Computer: Techniques and Prospects261990COMP448 summarisation Tue Mar 04 08:01:50 CET 2008IEEE Computer1129-36The Challenges of Automatic Summarization332000summarisation COMP448 Summarization--the art of abstracting key con-tent from one or more information sources--has become an integral part of everyday life. People keep abreast of world affairs by listening to news bites. They base investment decisions on stock market updates. They go to movies largely on the basis of reviews. With summaries, they can make effective decisions in less time. Although summarizing tools are available, with the increasing volume of online information, it is becoming harder to generate meaningful and timely summaries. Researchers are investigating tools and methods that automatically extract or abstract content from information sources. The authors describe how these data summarization methods fall into two categories. Knowledge-poor approaches rely on not having to add new rules for each new application domain or language. Knowledge-rich approaches assume that if you grasp the meaning of the text, you can reduce it more effectively, thus yielding a better summary. They rely on a size-able knowledge base of rules, which must be acquired, maintained, and then adapted to new applications and languages. The authors predict that summarization tools will be key in conquering the vast information universes ahead.Tue Mar 04 08:01:30 CET 2008OxfordThe Oxford Handbook of Computational Linguistics32583--598Oxford Handbooks in LinguisticsText Summarization2003COMP448 summarisation This chapter describes research and development on the automated creation of summaries of one or more texts. It presents an overview of the principal approaches in summarization, describes the design, implementation, and performance of various summarization systems, and reviews methods of evaluating summaries.