BibSonomy publications for /user/diego_ma/summarisationMon Mar 01 08:58:21 CET 2010Computational LinguisticsSeptember3297--328Sentence Fusion for Multidocument News Summarization312005summarisation Thu Feb 04 04:12:52 CET 2010Athens, GreeceProceedings of Conference of the European Chapter of the Association for Computational Linguistics(EACL 2009)Improving Grammaticality in Statistical Sentence Generation: Introducing a Dependency Spanning Tree Algorithm with an Argument Satisfaction Model2009summarisation Thu Feb 04 04:07:35 CET 2010Proceedings of the International Conference on User Modelling, Adaptation and Presentation (UMAP 2009)Capturing the User's Reading Context for Tailoring Summaries2009summarisation The web has become a major source of information to learn about a topic. With the continuous growth of information and its high connectivity, it is hard to follow only the links that are relevant and not to get lost in hyperspace. Our aim is to support people who read documents in a highly connected information space, helping them remain on focus. Our contextually-aware in-browser text summarisation tool, IBES, does this by capturing users? current interests and providing users with contextualised summaries of linked documents, to help them decide whether the link is worth following.Thu Feb 04 02:56:27 CET 2010Austin, TexasProceedings of the 2009 Joint Conference on Digital Libraries59-69Whetting the Appetite of Scientists: Producing Summaries Tailored to the Citation Context2009summarisation Wed Feb 03 05:39:40 CET 2010New Orleans, Louisiana, USAProceedings of SIGIR 2001349--357Finding Topic Words for Hierarchical Summarization2001summarisation Wed Feb 03 05:37:58 CET 2010Proceedings of the ACL/EACL 1997 Workshop on Intelligent Scalable Text Summarization10--17Using lexical chains for text summarization1997summarisation Wed Feb 03 05:33:46 CET 2010Proceedings of Document Understanding Conferences6-8A Keyphrase-Based Approach to Summarization:the LAKE System2005summarisation Wed Oct 21 23:12:15 CEST 2009Proceedings TAC 200810 pagesSummarisation Evaluation Using Transformed Basic Elements2008TAC summarisation This paper describes BEwT­E (Basic Elements with Transformations for Evaluation),   an automatic system for summarization evaluation. BEwT­E is a new, more sophisticated implementation of the BE framework that uses transformations to match BEs (minimal­length syntactically well­formed units) that are lexically different yet semantically similar. We demonstrate the effectiveness of BEwT­E using DUC and TAC datasets.Wed Oct 21 23:09:17 CEST 2009Proceedings CICLING 200815-26Summarization by Logic Segmentation and Text Entailment332008summarisation entailment Wed Oct 21 23:09:17 CEST 2009Information Processing \& Management1619-1642Satisfying Information Needs with Multi-document Summaries432007summarisation question_answering Generating summaries that meet the information needs of a user relies on (1) several forms of question decomposition; (2) different summarization approaches; and (3) textual inference for combining the summarization strategies. This novel framework for summarization has the advantage of producing highly responsive summaries, as indicated by the evaluation results.Fri Aug 28 21:47:37 CEST 2009Proceedings ACLAnswer Extraction, Semantic Clustering, and Extractive Summarization for Clinical Question Answering.2006clinical clustering question_answering summarisation Mon Aug 17 09:24:28 CEST 2009Proc. TAC 2008Overview of the TAC 2008 Opinion Question Answering and Summarization Tasks2008summarisation question_answering Mon Jul 06 09:40:30 CEST 2009DraftSummarizing Scientific Articles --- Experiments with Relevance and Rhetorical Status2001rhetorical_theory RTS summarisation In this article we propose a strategy for the summarization of scientific articles that concentrates on the rhetorical status of statements in an article: Material for summaries is selected in such a way that summaries can highlight the new contribution of the source article and situate it with respect to earlier work. We provide a gold standard for summaries of this kind consisting of a substantial corpus of conference articles in computational linguistics annotated with human judgements of the rhetorical status and relevance of each sentence in the articles. We present several experiments measuring our jugdes' agreement on these annotations. We also present an algorithm that, on the basis of the annotated training material, selects content from unseen articles and classifies it into a fixed sed of seven rhetorical categories. The output of this extraction and classification system can be viewed as a single-document summary in its own right; alternatively, it provides starting material for the generation of task-oriented and user-tailored summaries designed to give users an overview of a scientific field.Mon Jul 06 09:33:52 CEST 2009Information Processing \& Management20-34Automatic Generic Document Summarization Based on Non-negative Matrix Factorization452009document_summarisation summarisation In existing supervised methods, Latent Semantic Analysis (LSA) is used for sentence selection. However, the obtained results are less meaningful, because singular vectors are used as the bases for sentence selection from given documents, and singular vector components can have negative values. We propose a new unsupervised method using Non-negative Matrix Factorization (NMF) to select sentences for automatic generic document summarization. The proposed method uses non-negative constraints, which are more similar to the human cognition process. As a result, the method selects more meaningful sencntes for generic document summarization than those selected using LSA.Fri Mar 27 08:55:30 CET 2009Proc. Document Understanding Workshop10 pagesOverview of {DUC} 20062006summarisation The DUC 2006 summarization task was to synthesize from a set of 25 documents a well-organized, fluent answer to a complex question. The task and evaluation measures were basically the same as in DUC 2005, except that an additional "overall" responsiveness measure was added which took into account both content and readability of the summary. The average performance of systems in 2006 was noticeably better than in 2005; systems achieved better focus on average, and many attempted to provide greater coherence to their summaries. The overall responsiveness metric showed that readability plays an important role in the perceived quality of the summaries.Thu Feb 12 00:28:46 CET 2009Information Processing and Management135-41Using query expansion in graph-based approach for query-focused multi-document summarization.452009summarisation question_answering graphs This paper presents a novel query expansion method, which is combined in the graph-based algorithm for query-focused multi-document summarization, so as to resolve the problem of information limit in the original query. Our approach makes use of both the sentence-to-sentence relations and the sentence-to-word relations to select the query biased informative words from the document set and use them as query expansions to improve the sentence ranking result. Compared to previous query expansion approaches, our approach can capture more relevant information with less noise. We performed experiments on the data of document understanding conference (DUC) 2005 and DUC 2006, and the evaluation results show that the proposed query expansion method can significantly improve the system performance and make our system comparable to the state-of-the-art systems.Thu Jan 29 00:41:51 CET 2009Proceedings of the 22nd annual international ACM SIGIR conference on Research and development in information retrievalconf/sigir/99137-144The Automatic Construction of Large-Scale Corpora for Summarization Research.1999tools corpora summarisation Summarization research is notorious for its lack of adequatecorpora: today, there exist only a few small collections oftexts whose units have been manually annotated for textualimportance. Given the cost and tediousness of the annota-tion process, it is very unlikely that we will ever manuallyannotate for textual importance sufficiently large corpora oftexts. To circumvent this problem, we have developed analgorithm that constructs such corpora automatically.Our algorithm takes as input an $<$Abstract, Text$>$ tuple andgenerates the corresponding Extract, i.e., the set of clauses(sentences) in the Text that were used to write the Abstract.The performance of the algorithm is shown to be close to thatof humans by means of an empirical experiment. The exper-iment also suggests extraction strategies that could improvethe performance of automatic summarization systems.Wed Mar 19 05:51:36 CET 2008Proc. ACM conference on Information and Knowledge Management (CIKM)8 pagesTraining a Selection Function for Extraction1999summarisation COMP448 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 summaries2004summarisation evaluation COMP448 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.