Abstract
Text summarization aims to generate a single, concise representation for documents. For Web applications, documents related to an event retrieved by search engines usually describe several event phases implicitly, making it difficult for existing approaches to identify, extract and summarize these phases. In this paper, we aim to mine and summarize event phases automatically from a stream of news data on the Web. We model the semantic relations of news via a graph model called Temporal Content Coherence Graph. A structural clustering algorithm EPCluster is designed to separate news articles corresponding to event phases. After that, we calculate the relevance of news articles based on a vertex-reinforced random walk algorithm and generate event phase summaries in a relevance maximum optimization framework. Experiments on news datasets illustrate the effectiveness of our approach.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
See background info at: https://en.wikipedia.org/wiki/Egyptian_Revolution_of_2011.
- 2.
One issue that needs to be discussed here is that because our dataset is relatively large and there are over k news articles in each cluster regarding an event phase, we set a uniform parameter k for all the event phases. We can also modify the definition such that k varies for different event phases without changing our algorithm.
- 3.
In the implementation, we set one day as a time slot and compute \(w_t(\cdot )\) based on publication date difference. See Fig. 1(a) and (b).
- 4.
Based on the definition, we can see that each news article \(d_i\) and node \(v_i\) has a one-to-one correspondence relationship. In the following, without ambiguity, we will use \(d_i\) to represent a node and a news article interchangeably.
- 5.
Many other methods focus on timeline generation. However, the summaries we generates are headlines and dates, making it difficult to compare our method with them. We will investigate how to modify these algorithms for our task in the future.
References
Gong, Y., Liu, X.: Generic text summarization using relevance measure and latent semantic analysis. In: SIGIR, pp. 19–25 (2001)
Conroy, J.M., O’Leary, D.P.: Text summarization via hidden markov models. In: SIGIR, pp. 406–407 (2001)
He, Z., Chen, C., Bu, J., Wang, C., Zhang, L., Cai, D., He, X.: Document summarization based on data reconstruction. In: AAAI (2012)
Qian, X., Liu, Y.: Fast joint compression and summarization via graph cuts. In: EMNLP, pp. 1492–1502 (2013)
Yan, R., Kong, L., Huang, C., Wan, X., Li, X., Zhang, Y.: Timeline generation through evolutionary trans-temporal summarization. In: EMNLP, pp. 433–443 (2011)
Tran, G., Alrifai, M., Herder, E.: Timeline summarization from relevant headlines. In: Hanbury, A., Kazai, G., Rauber, A., Fuhr, N. (eds.) ECIR 2015. LNCS, vol. 9022, pp. 245–256. Springer, Heidelberg (2015). doi:10.1007/978-3-319-16354-3_26
Erkan, G., Radev, D.R.: Lexrank: graph-based lexical centrality as salience in text summarization. J. Qiqihar Junior Teachers Coll. 22, 2004 (2011)
Wan, X., Yang, J.: Multi-document summarization using cluster-based link analysis. In: SIGIR, pp. 299–306 (2008)
Ng, J., Chen, Y., Kan, M., Li, Z.: Exploiting timelines to enhance multi-document summarization. In: ACL, pp. 923–933 (2014)
Chen, C.C., Chen, Y.-T., Sun, Y., Chen, M.C.: Life cycle modeling of news events using aging theory. In: Lavrač, N., Gamberger, D., Blockeel, H., Todorovski, L. (eds.) ECML 2003. LNCS (LNAI), vol. 2837, pp. 47–59. Springer, Heidelberg (2003). doi:10.1007/978-3-540-39857-8_7
Knights, D., Mozer, M.C., Nicolov, N.: Detecting topic drift with compound topic models. In: ICWSM (2009)
Blei, D.M., Ng, A.Y., Jordan, M.I.: Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003)
Wang, C., Zhang, R., He, X., Zhou, A.: Nerank: ranking named entities in document collections. In: WWW, pp. 123–124 (2016)
De Kretser, O., Moffat, A.: Effective document presentation with a locality-based similarity heuristic. In: SIGIR, pp. 113–120 (1999)
Xu, X., Yuruk, N., Feng, Z., Schweiger, T.A.J.: SCAN: a structural clustering algorithm for networks. In: KDD, pp. 824–833 (2007)
Brin, S., Page, L.: The anatomy of a large-scale hypertextual web search engine. Comput. Netw. 30(1–7), 107–117 (1998)
Pemantle, R.: Vertex-reinforced random walk. Probab. Theory Relat. Fields 92(1), 117–136 (1992)
Mei, Q., Guo, J., Radev, D.R.: Divrank: the interplay of prestige and diversity in information networks. In: KDD, pp. 1009–1018 (2010)
Khuller, S., Moss, A., Naor, J.S.: The budgeted maximum coverage problem. Inf. Process. Lett. 70(1), 39–45 (1999)
Chen, J., Niu, Z., Fu, H.: A multi-news timeline summarization algorithm based on aging theory. In: Cheng, R., Cui, B., Zhang, Z., Cai, R., Xu, J. (eds.) APWeb 2015. LNCS, vol. 9313, pp. 449–460. Springer, Heidelberg (2015). doi:10.1007/978-3-319-25255-1_37
Lin, C., Hovy, E.H.: Automatic evaluation of summaries using n-gram co-occurrence statistics. In: HLT-NAACL (2003)
Chieu, H.L., Lee, Y.K.: Query based event extraction along a timeline. In: SIGIR, pp. 425–432 (2004)
Acknowledgements
This work is partially supported by the National Key Research and Development Program of China under Grant No. 2016YFB1000904, Shanghai Agriculture Science Program (2015) Number 3-2 and NSFC-Zhejiang Joint Fund for the Integration of Industrialization and Informatization under Grant No. U1509219.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing AG
About this paper
Cite this paper
Wang, C., Zhang, R., He, X., Zhou, G., Zhou, A. (2016). Event Phase Extraction and Summarization. In: Cellary, W., Mokbel, M., Wang, J., Wang, H., Zhou, R., Zhang, Y. (eds) Web Information Systems Engineering – WISE 2016. WISE 2016. Lecture Notes in Computer Science(), vol 10041. Springer, Cham. https://doi.org/10.1007/978-3-319-48740-3_35
Download citation
DOI: https://doi.org/10.1007/978-3-319-48740-3_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-48739-7
Online ISBN: 978-3-319-48740-3
eBook Packages: Computer ScienceComputer Science (R0)