The Value of Weights in Automatically Generated Text Structures

  • Dana Dannélls
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5449)


One question that arises if we want to evolve generation techniques to accommodate Web ontologies is how to capture and expose the relevant ontology content to the user. This paper presents an attempt to answer the question about how to select the ontology statements that are significant for the user and present those statements in a way that helps the user to learn. Our generation approach combines bottom-up and top-down techniques with enhanced comparison methods to tailor descriptions about a concept described in an ontology. A preliminary evaluation indicates that the process of computing preferable property weights in addition to enhanced generation methods has a positive effect on the text structure and its content. Future work aims to assign grammar rules and lexical entries in order to produce coherent texts that follow on from the generated text structures in several languages.


NLG Ontology Semantic Web 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Androutsopoulos, I., Kokkinaki, V., Dimitromanolaki, A., Calder, J., Oberl, J., Not, E.: Generating multilingual personalized descriptions of museum exhibits: the m-piro project. In: Proceedings of the International Conference on Computer Applications and Quantitative Methods in Archaeology (2001)Google Scholar
  2. 2.
    Berners-lee, T.: Semantic Web Road Map. W3C Design Issues (October 1998),
  3. 3.
    Bontcheva, K.: Generating tailored textual summaries from ontologies. In: Gómez-Pérez, A., Euzenat, J. (eds.) ESWC 2005. LNCS, vol. 3532, pp. 531–545. Springer, Heidelberg (2005)CrossRefGoogle Scholar
  4. 4.
    Bontcheva, K., Wilks, Y.: Automatic report generation from ontologies: The MIAKT approach. In: Meziane, F., Métais, E. (eds.) NLDB 2004. LNCS, vol. 3136, pp. 324–335. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  5. 5.
    Bouayad-Agha, N., Power, R., Scott, D.: Can text structure be incompatible with rhetorical structure? In: Proceedings of First International Natural Language Generation Conference (INLG), pp. 194–200 (2000)Google Scholar
  6. 6.
    Capra, R., Marchionini, G., Oh, J.S., Stutzman, F., Zhang, Y.: Effects of structure and interaction style on distinct search tasks. In: JCDL 2007: Proceedings of the 2007 conference on Digital libraries, pp. 442–451. ACM Press, New York (2007)CrossRefGoogle Scholar
  7. 7.
    Clough, P., Marlow, J., Ireson, N.: Enabling semantic access to cultural heritage: A case study of tate online. In: Proceedings of the ECDL. Workshop on Information Access to Cultural Heritage, Aarhus, Denmark (2008) ISBN 978-90-813489-1-1Google Scholar
  8. 8.
    Dale, R., Reiter, E.: Computational interpretations of the gricean maxims in the generation of referring expressions. Cognitive Science 19, 233–263 (1994)CrossRefGoogle Scholar
  9. 9.
    Dannélls, D.: A system architecture for conveying historical knowledge to museum visitors. In: Proceedings of the 12th European Conference On Research And Advanced Technology For Digital Libraries (ECDL) Workshop on Information Access to Cultural Heritage, Aarhus, Denmark (2008) ISBN 978-90-813489-1-1Google Scholar
  10. 10.
    Doerr, M., Ore, C.E., Stead, S.: The cidoc conceptual reference model: a new standard for knowledge sharing. In: ER 2007: Tutorials, posters, panels and industrial contributions at the 26th International Conference on Conceptual Modeling (2007)Google Scholar
  11. 11.
    Hardcastle, D., Scott, D.: Can we evaluate the quality of generated text? In: The 6th edition of the Language Resources and Evaluation Conference (LREC 2008), Marrakech, Morocco (2008)Google Scholar
  12. 12.
    Isard, A.: Choosing the best comparison under the circumstances. In: Proceedings of the International Workshop on Personalization Enhanced Access to Cultural Heritage (PATCH 2007) (2007)Google Scholar
  13. 13.
    Johansson, P., Degerstedt, L., Jönsson, A.: Iterative development of an information-providing dialogue system. In: Proceedings of 7th European Research Consortium for Informatics and Mathematics (ERCIM) Workshop (2002)Google Scholar
  14. 14.
    Mellish, C., Knott, A., Oberlander, J.: Experiments using stochastic search for text planning. In: International Conference on Natural Language Generation (1998)Google Scholar
  15. 15.
    Mellish, C., Oberlander, J., Knott, A.: An architecture for opportunistic text generation. In: The Ninth International Workshop on Natural Language Generation (1998)Google Scholar
  16. 16.
    Mellish, C., Pan, J.Z.: Natural language directed inference from ontologies. Artificial Intelligence 172, 1285–1315 (2008)MathSciNetCrossRefzbMATHGoogle Scholar
  17. 17.
    Milosavljevic, M.: Content selection in comparison generation. In: The 6th European Workshop on Natural Language Generation (6th EWNLG) (1997)Google Scholar
  18. 18.
    O’Donnell, M.J., Mellish, C., Oberlander, J., Knott, A.: ILex: An architecture for a dynamic hypertext generation system. Natural Language Engineering 7, 225–250 (2001)Google Scholar
  19. 19.
    Reiter, E.: Has a consensus NLG architecture appeared and is it psycholinguistically plausible? In: Proceedings of the Seventh International Workshop on Natural Language Generation, Kennebunkport, Maine, pp. 163–170 (1994)Google Scholar
  20. 20.
    Reiter, E., Dale, R.: Building Natural Language Generation Systems. MIT Press and The McGraw-Hill Companies,Inc., Singapore (2000)CrossRefGoogle Scholar
  21. 21.
    Wilcock, G.: Talking owls: Towards an ontology verbalizer. In: Human Language Technology for the Semantic Web and Web Services, Sanibel Island, Florida, pp. 109–112 (2003)Google Scholar
  22. 22.
    Wilcock, G., Jokinen, K.: Generating responses and explanations from rdf/xml and daml+oil. In: Knowledge and Reasoning in Practical Dialogue Systems IJCAI, Acapulco, pp. 58–63 (2003)Google Scholar
  23. 23.
    Young, M.R.: Using grice’s maxim of quantity to select the content of plan descriptions. Artificial Intelligence 115, 215–256 (1999)CrossRefzbMATHGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Dana Dannélls
    • 1
  1. 1.NLP Research Unit, Department of Swedish LanguageUniversity of GothenburgSweden

Personalised recommendations