Summary Generation for Temporal Extractions

  • Yafang Wang
  • Zhaochun Ren
  • Martin Theobald
  • Maximilian Dylla
  • Gerard de Melo
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9827)


Recent advances in knowledge harvesting have enabled us to collect large amounts of facts about entities from Web sources. A good portion of these facts have a temporal scope that, for example, allows us to concisely capture a person’s biography. However, raw sets of facts are not well suited for presentation to human end users. This paper develops a novel abstraction-based method to summarize a set of facts into natural-language sentences. Our method distills temporal knowledge from Web documents and generates a concise summary according to a particular user’s interest, such as, for example, a soccer player’s career. Our experiments are conducted on biography-style Wikipedia pages, and the results demonstrate the good performance of our system in comparison to existing text-summarization methods.


Temporal information extraction Knowledge harvesting Summarization 


  1. 1.
    Arora, R., Ravindran, B.: Latent Dirichlet allocation based multi-document summarization. In: Second Workshop on Analytics for Noisy Unstructured Text Data (AND), pp. 91–97. ACM (2008)Google Scholar
  2. 2.
    Auer, S., Bizer, C., Kobilarov, G., Lehmann, J., Cyganiak, R., Ives, Z.G.: DBpedia: a nucleus for a web of open data. In: Aberer, K., et al. (eds.) ASWC 2007 and ISWC 2007. LNCS, vol. 4825, pp. 722–735. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  3. 3.
    Bing, L., Li, P., Liao, Y., Lam, W., Guo, W., Passonneau, R.J.: Abstractive multi-document summarization via phrase selection and merging. In: ACL, pp. 1587–1597 (2015)Google Scholar
  4. 4.
    Carlson, A., Betteridge, J., Wang, R.C., Hruschka Jr., E.R., Mitchell, T.M.: Coupled semi-supervised learning for information extraction. In: WSDM (2010)Google Scholar
  5. 5.
    Chhabra, S., Bedathur, S.: Towards generating text summaries for entity chains. In: de Rijke, M., Kenter, T., de Vries, A.P., Zhai, C.X., de Jong, F., Radinsky, K., Hofmann, K. (eds.) ECIR 2014. LNCS, vol. 8416, pp. 136–147. Springer, Heidelberg (2014)CrossRefGoogle Scholar
  6. 6.
    Conroy, J., O’leary, D.: Text summarization via hidden Markov models. In: SIGIR, pp. 406–407. ACM (2001)Google Scholar
  7. 7.
    Fader, A., Soderland, S., Etzioni, O.: Identifying relations for open information extraction. In: EMNLP, Edinburgh, Scotland, UK, pp. 1535–1545, 27–31 July 2011Google Scholar
  8. 8.
    Filippova, K.: Multi-sentence compression: finding shortest paths in word graphs. In: ACL, pp. 322–330 (2010)Google Scholar
  9. 9.
    Ganesan, K., Zhai, C., Han, J.: Opinosis: a graph-based approach to abstractive summarization of highly redundant opinions. In: ACL, pp. 340–348 (2010)Google Scholar
  10. 10.
    Hoffart, J., Yosef, M.A., Bordino, I., Fürstenau, H., Pinkal, M., Spaniol, M., Thater, S., Weikum, G.: Robust disambiguation of named entities in text. In: EMNLP, pp. 782–792 (2011)Google Scholar
  11. 11.
    Hong, K., Marcus, M., Nenkova, A.: System combination for multi-document summarization. In: EMNLP, pp. 107–117 (2015)Google Scholar
  12. 12.
    Knight, K., Marcu, D.: Summarization beyond sentence extraction: a probabilistic approach to sentence compression. Artif. Intell. 139(1), 91–107 (2002)MathSciNetCrossRefMATHGoogle Scholar
  13. 13.
    Li, L., Zhou, K., Xue, G., Zha, H., Yu, Y.: Enhancing diversity, coverage and balance for summarization through structure learning. In: WWW, pp. 71–80. ACM (2009)Google Scholar
  14. 14.
    Ling, X., Weld, D.S.: Temporal information extraction. In: AAAI, pp. 1385–1390, 11–15 July 2010Google Scholar
  15. 15.
    Liu, F., Flanigan, J., Thomson, S., Sadeh, N.M., Smith, N.A.: Toward abstractive summarization using semantic representations. In: NAACL, pp. 1077–1086 (2015)Google Scholar
  16. 16.
    Mani, I.: Summarization evaluation: an overview (2001)Google Scholar
  17. 17.
    McClosky, D., Manning, C.D.: Learning constraints for consistent timeline extraction. In: EMNLP-CoNLL, pp. 873–882 (2012)Google Scholar
  18. 18.
    McDonald, D., Pustejovsky, J.: Natural language generation. In: IJCAI. Citeseer (1986)Google Scholar
  19. 19.
    Radev, D., Allison, T., Blair-Goldensohn, S., Blitzer, J., Celebi, A., Dimitrov, S., Drabek, E., Hakim, A., Lam, W., Liu, D., et al.: MEAD-a platform for multidocument multilingual text summarization. In: LREC, vol. 2004 (2004)Google Scholar
  20. 20.
    Schluter, N., Søgaard, A.: Unsupervised extractive summarization via coverage maximization with syntactic and semantic concepts. In: ACL, pp. 840–844 (2015)Google Scholar
  21. 21.
    Shen, D., Sun, J., Li, H., Yang, Q., Chen, Z.: Document summarization using conditional random fields. IJCAI 7, 2862–2867 (2007)Google Scholar
  22. 22.
    Suchanek, F.M., Kasneci, G., Weikum, G.: YAGO: a core of semantic knowledge. In: WWW, pp. 697–706. ACM, New York (2007)Google Scholar
  23. 23.
    Sydow, M., Pikula, M., Schenkel, R.: The notion of diversity in graphical entity summarisation on semantic knowledge graphs. J. Intell. Inf. Syst. 41(2), 109–149 (2013)CrossRefGoogle Scholar
  24. 24.
    Takaku, Y., Kaji, N., Yoshinaga, N., Toyoda, M.: Identifying constant and unique relations by using time-series text. In: EMNLP-CoNLL, pp. 883–892 (2012)Google Scholar
  25. 25.
    Talukdar, P.P., Crammer, K.: New regularized algorithms for transductive learning. In: Buntine, W., Grobelnik, M., Mladenić, D., Shawe-Taylor, J. (eds.) ECML PKDD 2009, Part II. LNCS, vol. 5782, pp. 442–457. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  26. 26.
    Talukdar, P.P., Wijaya, D., Mitchell, T.: Coupled temporal scoping of relational facts. In: WSDM. Association for Computing Machinery, Seattle, February 2012Google Scholar
  27. 27.
    Tylenda, T., Sozio, M., Weikum, G.: Einstein: physicist or vegetarian? Summarizing semantic type graphs for knowledge discovery. In: WWW (Companion Volume), pp. 273–276 (2011)Google Scholar
  28. 28.
    Wan, X., Yang, J.: Multi-document summarization using cluster-based link analysis. In: SIGIR, pp. 299–306. ACM (2008)Google Scholar
  29. 29.
    Wang, Y., Dylla, M., Spaniol, M., Weikum, G.: Coupling label propagation and constraints for temporal fact extraction. In: ACL, vol. 2, pp. 233–237 (2012)Google Scholar
  30. 30.
    Wang, Y., Yahya, M., Theobald, M.: Time-aware reasoning in uncertain knowledge bases. In: MUD, pp. 51–65 (2010)Google Scholar
  31. 31.
    Wang, Y., Yang, B., Qu, L., Spaniol, M., Weikum, G.: Harvesting facts from textual web sources by constrained label propagation. In: CIKM, pp. 837–846 (2011)Google Scholar
  32. 32.
    Zhang, X., Cheng, G., Qu, Y.: Ontology summarization based on RDF sentence graph. In: WWW, pp. 707–716 (2007)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  • Yafang Wang
    • 1
  • Zhaochun Ren
    • 2
  • Martin Theobald
    • 3
  • Maximilian Dylla
    • 4
  • Gerard de Melo
    • 5
  1. 1.Shandong UniversityJinanChina
  2. 2.University of AmsterdamAmsterdamThe Netherlands
  3. 3.University of UlmUlmGermany
  4. 4.Max Planck Institute of InformaticsSaarbrückenGermany
  5. 5.Tsinghua UniversityBeijingChina

Personalised recommendations