Abstract
This paper proposes an abstractive multi-document summarization method. Given a document set, the system first generates sentence clusters through an event clustering algorithm using distributed representation. Each cluster is regarded as a subtopic of this set. Then we use a novel multi-sentence compression method to generate K-shortest paths for each cluster. Finally, some preferable paths are selected from these candidates to construct the final summary based on several customized submodular functions, which are designed to measure the summary quality from different perspectives. Experimental results on DUC 2005 and DUC 2007 datasets demonstrate that our method achieves better performance compared with the state-of-the-art systems.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
- 2.
- 3.
- 4.
- 5.
- 6.
- 7.
We use Sent2Vec, which code is available at https://github.com/klb3713/sentence2vec, to learn the vectors of sentences.
References
Banerjee, S., Mitra, P., Sugiyama, K.: Multi-document abstractive summarization using ILP based multi-sentence compression. In: Proceedings of IJCAI 2015, pp. 1208–1214 (2015)
Barzilay, R., McKeown, K.R.: Sentence fusion for multidocument news summarization. Comput. Linguist. 31(3), 297–328 (2005)
Biemann, C.: Chinese whispers: an efficient graph clustering algorithm and its application to natural language processing prob-lems. In: Proceedings of the First Workshop on Graph Based Methods for Natural Language Processing, pp. 73–80 (2006)
Bing, L., Li, P., Liao, Y., Lam, W.: Abstractive multi-document summarization via phrase selection and merging. In: Proceedings of ACL 2015, pp. 1587–1597 (2015)
Cheung, J.C.K., Penn, G.: Towards robust abstractive multi-document summarization: a caseframe analysis of centrality and domain. In: Proccedings of ACL 2013, pp. 775–786 (2013)
Cheung, J.C.K., Penn, G.: Unsupervised sentence enhancement for automatic. In: Proccedings of EMNLP 2014, pp. 775–786 (2014)
Dasgupta, A., Kumar, R., Ravi, S.: Summarization through submodularity and dispersion. In: Proccedings of ACL 2013, pp. 1014–1022 (2013)
Ding, X., Zhang, Y., Liu, T., Duan, J.: Using structured events to predict stock price movement: an empirical investigation. In: Proceedings of EMNLP 2014, pp. 1415–1425 (2014)
Fader, A., Soderland, S., Etzioni, O.: Identifying relations for open. In: Proceedings of EMNLP 2011, pp. 1535–1545 (2011)
Filippovai, K.: Multi-sentence compression: finding shortest paths in word graphs. In: Proceedings of Coling 2010, pp. 322–330 (2010)
Genest, P.-E., Lapalme, G.: Framework for abstractive summarization using text-to-text generation. In: Proceedings of the Workshop on Monolingual Text-To-Text Generation, pp. 64–73 (2011)
Grefenstette, E., Sadrzadeh, M.: Experimental support for a categorical compositional distributional model of meaning. In: Proceedings of EMNLP 2011, pp. 1394–1404 (2011)
Hu, Z., Rahimtoroghi, E., Munishkina, L., Swanson, R., Walker, M.A.: Unsupervised induction of contingent event pairs from film scenes. In: Proceedings of EMNLP 2013, pp. 369–379 (2013)
Li, C., Liu, Y., Liu, F., Zhao, L., Weng, F.: Improving multi-documents summarization by sentence compression based on expanded constituent parse trees. In: Proceedings of EMNLP 2014, pp. 691–701 (2014)
Li, P., Bing, L., Lam, W., Li, H., Liao, Y.: Reader-aware multi-document summarization via sparse coding. In: Proceedings of IJCAI 2015, pp. 30–35 (2015)
Li, W.: Abstractive multi-document summarization with semantic information extraction. In: Proceedings of EMNLP 2015, pp. 1908–1913 (2015)
Lin, H., Bilmes, J.: A class of submodular functions for document summarizatio. In: Proccedings of ACL 2011, pp. 510–520 (2011)
Lin, C.-Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branckes Out: Proceedings of the ACL-04 Workshop, pp. 74–81 (2004)
Liu, F., Flanigan, J., Thomson, S., Dadeh, N., Smith, N.A.: Toward abstractive summarization using semantic representations. In: Proceedings of NAACL 2015, pp. 1077–1086 (2015)
Mani, I.: Automatic Summarization. Natural Language Processing, vol. 3. John Benjamins Publishing Company, Amsterdam (2001)
McDonald, R.: A study of global inference algorithms in multi-document summarization. In: Amati, G., Carpineto, C., Romano, G. (eds.) ECiR 2007. LNCS, vol. 4425, pp. 557–564. Springer, Heidelberg (2007)
Mehdad, Y., Carenini, G., Ng, R.T.: Abstractive summarization of spoken and written conversations based on phrasal queries. In: Proceedings of ACL 2014, pp. 1220–1230 (2014)
Ng, J.-P., Chen, Y., Kan, M.-Y., Li, Z.: Exploiting timelines to enhance multi-document summarization. In: Proceedings of ACL 2014, pp. 923–933 (2014)
Sun, R., Zhang, Y., Zhang, M., Ji, D.: Event-driven headline generation. In: Proceedings of ACL 2015, pp. 462–472 (2015)
Zhang, Y.: Partial-tree linearization: generalized word ordering for text synthesis. In: Proceedings of IJCAI 2013, pp. 2232–2238 (2013)
Zheng, H.-T., Gong, S.-Q., Chen, H., Jiang, Y., Xia, S.-T.: Multi-document summarization based on sentence clustering. In: Neural Information Processing, pp. 429–436 (2014)
Acknowledgments
We thank all reviewers for their detailed comments. This work is supported by the State Key Program of National Natural Science Foundation of China (Grant 61133012), the National Natural Science Foundation of China (Grant 61373108, 61373056), the National Philosophy Social Science Major Bidding Project of China (Grant 11&ZD189). The corresponding author of this paper is Donghong Ji.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Sun, R., Wang, Z., Ren, Y., Ji, D. (2016). Query-Biased Multi-document Abstractive Summarization via Submodular Maximization Using Event Guidance. In: Cui, B., Zhang, N., Xu, J., Lian, X., Liu, D. (eds) Web-Age Information Management. WAIM 2016. Lecture Notes in Computer Science(), vol 9658. Springer, Cham. https://doi.org/10.1007/978-3-319-39937-9_24
Download citation
DOI: https://doi.org/10.1007/978-3-319-39937-9_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-39936-2
Online ISBN: 978-3-319-39937-9
eBook Packages: Computer ScienceComputer Science (R0)