A Hybrid Sentence Ordering Strategy in Multi-document Summarization
In extractive summarization, a proper arrangement of extracted sentences must be found if we want to generate a logical, coherent and readable summary. This issue is special in multi-document summarization. In this paper, several existing methods each of which generate a reference relation are combined through linear combination of the resulting relations. We use 4 types of relationships between sentences (chronological relation, positional relation, topical relation and dependent relation) to build a graph model where the vertices are sentences and edges are weighed relationships of the 4 types. And then apply a variation of page rank to get the ordering of sentences for multi-document summaries. We tested our hybrid model with two automatic methods: distance to manual ordering and ROUGE score. Evaluation results show a significant improvement of the ordering over strategies losing some relations. The results also indicate that this hybrid model is robust for articles with different genre which were used on DUC2004 and DUC2005.
KeywordsHybrid Model Dependent Relation Precedence Graph Chronological Relation Document Summarization
Unable to display preview. Download preview PDF.
- 1.Mani, I.: Automatic Summarization. John Benjamins (2001) Google Scholar
- 5.Lapata, M.: Probabilistic text structuring: experiments with sentence ordering. In: Proceedings of the 41st Meeting of the Association of Computational Linguistics, pp. 545–552 (2003)Google Scholar
- 6.Asher, N., Lascarides, A.: Logics of Conversation. Cambridge University Press, Cambridge (2003)Google Scholar
- 7.Grosz, B., Joshi, A., Weinstein, S.: Centering: A framework for modeling the local coherence of discourse. Computational Linguistics 21(2), 203–225 (1995)Google Scholar
- 11.Mihalcea, R., Tarau, P.: A Language Independent Algorithm for Single and Multiple Document Summarization (2005), http://acl.ldc.upenn.edu/I/I05/
- 12.Paul, O., James, Y.: An Introduction to DUC 2004. In: Proceedings of the 4th Document Understanding Conference (DUC 2004) (2004)Google Scholar
- 13.Lin, C.Y., Hovy, E.: Automatic Evaluation of Summaries Using N-gram Co-Occurrence Statistics. In: Proceedings of the Human Technology Conference (HLTNAACL 2003), Edmonton, Canada (2003)Google Scholar
- 14.Dang, H.T.: Overview of DUC 2005 (DRAFT). In: Proceedings of the 5th Document Understanding Conference (DUC 2005) (2005)Google Scholar
- 15.Lebanon, G., Lafferty, J.: Combining rankings using conditional probability models on permutations. In: Proceedings of the 19th International Conference on Machine Learning, pp. 363–370. Morgan Kaufmann Publishers, San Francisco (2002)Google Scholar