A context-aware study for sentence ordering
- 93 Downloads
This paper proposes a context-aware method for sentence ordering in multi-document summarization task, which combines support vector machine (SVM) and Grey Model (GM). Multi-Documents summarization task focus on how to extract main information of document set, this paper aim to prove the coherence of summary based on the context of document set. Firstly, the method trains the SVM with sentences of each source document and predict sentences sequence of summary as primary dataset. Secondly, using Grey Model to process the primary dataset, according to the analysis we achieve the final sequence of summary sentences. Experiments on 100 summaries shown this method provide a much higher precision than probabilistic model in sentence ordering task.
KeywordsContext-aware Sentence ordering Multi-document
Unable to display preview. Download preview PDF.
- 1.Barzilay, R., Elhadad, N., & McKeown, K. (2002). Inferring strategies for sentence ordering in multidocument news summarization. The Journal of Artificial Intelligence Research, 17, 35–55. Google Scholar
- 2.Madnani, N., Passonneau, R., Ayan, N. F., Conroy, J., Dorr, B., Klavans, J., O’Leary, D., & Schlesinger, J. (2007). Measuring variability in sentence ordering for news summarization. In Proceedings of the 11th European workshop on natural language generation, Schloss Dagstuhl, Germany, 17–20 June 2007 (pp. 81–88). CrossRefGoogle Scholar
- 3.Okazaki, N., Matsuo, Y., & Ishizuka, M. (2004). Improving chronological sentence ordering by precedence relation. In Proceedings of 20th international conference on computational linguistics (COLING), 2004 (pp. 750–756). Google Scholar
- 4.Lapata, M. (2003). Probabilistic text structuring: Experiments with sentence ordering. In Proceedings of the annual meeting of ACL, 2003 (pp. 545–552). Google Scholar
- 5.Barzilay, R., & Lee, L. (2004). Catching the drift: Probabilistic content models, with applications to generation and summarization. In HLT-NAACL 2004: proceedings of the main conference, 2004 (pp. 113–120). Google Scholar
- 6.Grosz, B., Joshi, A. K., & Weinstein, S. (1995). Centering: a framework for modeling the local coherence of discourse. Computational Linguistics, 21(2), 203–225. Google Scholar
- 7.Barzilay, R., Elhadad, N., & McKeown, K. R. (2001). Sentence ordering in multi-document summarization. In Proceedings of the 1st human language technology conference, 2001 (pp. 1–7). Google Scholar
- 8.Donghong, J., & Yu, N. (2008). Sentence ordering based on cluster adjacency in multi-document summarization. In The third international joint conference on natural language processing, 2008 (pp. 745–750). Google Scholar
- 9.Vapnik, V. (1982). Estimation of dependences based on empirical data. New York: Springer. Google Scholar
- 11.Salton, G., & McGill, M. J. (1983). Introduction to modern information retrieval. New York: McGraw-Hill. Google Scholar
- 12.Fukunaga, K. (1990). Introduction to statistical patten recognition. San Diego: Academic Press. Google Scholar
- 13.Ye, J. (2008). Generalized linear discriminant analysis: a unified framework and efficient model selection. IEEE Transactions on Neural Networks, 19(10), 1770. Google Scholar
- 14.Deng, J.-L. (2002). Grey Theory Base. Wuhan: Huazhong University of Science and Technology Press. Google Scholar
- 16.Liu, S.-F., & Xie, N.-M. (2008). The grey system theory and application (4rd edn.). Beijing: Science Press. Google Scholar
- 17.Lebanon, G., & Lafferty, J. (2002). Combining rankings using conditional probability models on permutations. In Proceedings of the 19th international conference on machine learning. Google Scholar
- 18.Lapata, M. (2002). Automatic Evaluation of Information Ordering: Kendall’s Tau. Association for Computational Linguistics, pp. 471–484. Google Scholar
- 19.Sogou Labs (2011). http://www.sogou.com/labs/dl/t.html.