Advertisement

Natural Language Generation through Case-Based Text Modification

  • Josep Valls
  • Santiago Ontañón
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7466)

Abstract

Natural Language Generation (NLG) is one of the longstanding problems in Artificial Intelligence. In this paper, we focus on a subproblem in NLG, namely surface realization through text modification: given a source sentence and a desired change, produce a grammatically correct and semantically coherent sentence that implements the desired change. Text modification has many applications within text generation like interactive narrative systems, where stories tailored to specific users are generated by adapting or instantiating a pre-authored story. We present a case-based approach where cases correspond to pairs of sentences implementing specific modifications. We describe our retrieval, adaptation and revise procedures. The main contribution of this paper is an approach to perform case-adaptation in textual domains.

Keywords

Ground Truth Language Model Candidate Solution Surface Realization Target Sentence 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Aamodt, A., Plaza, E.: Case-based reasoning; foundational issues, methodological variations, and system approaches. AI Communications 7(1), 39–59 (1994)Google Scholar
  2. 2.
    Adeyanju, I., Wiratunga, N., Lothian, R., Sripada, S., Lamontagne, L.: Case Retrieval Reuse Net (CR2N): An Architecture for Reuse of Textual Solutions. In: McGinty, L., Wilson, D.C. (eds.) ICCBR 2009. LNCS, vol. 5650, pp. 14–28. Springer, Heidelberg (2009)CrossRefGoogle Scholar
  3. 3.
    Apostolico, A.: String editing and longest common subsequences. In: Handbook of Formal Languages, pp. 361–398. Springer (1996)Google Scholar
  4. 4.
    Catherine De Marneffe, M., Manning, C.D.: Stanford typed dependencies manual (2008)Google Scholar
  5. 5.
    Etzioni, O., Cafarella, M., Downey, D., Popescu, A.-M., Shaked, T., Soderland, S., Weld, D.S., Yates, A.: Unsupervised named-entity extraction from the web: An experimental study. Artificial Intelligence 165, 91–134 (2005)CrossRefGoogle Scholar
  6. 6.
    Gervás, P., Hervás, R., Recio-García, J.A.: The role of natural language generation during adaptation in textual cbr. In: Workshop on Textual Case-Based Reasoning: Beyond Retrieval, in 7th International Conference on Case-Based Reasoning (ICCBR 2007), Northern Ireland, pp. 227–235 (August 2007)Google Scholar
  7. 7.
    Lewis, D.D.: Naive (Bayes) at Forty: The Independence Assumption in Information Retrieval. In: Nédellec, C., Rouveirol, C. (eds.) ECML 1998. LNCS, vol. 1398, pp. 4–15. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  8. 8.
    Metzler, D., Dumais, S., Meek, C.: Similarity measures for short segments of text. In: European Conference on Information Retrieval (2007)Google Scholar
  9. 9.
    Ontañón, S., Zhu, J.: Story and Text Generation through Computational Analogy in the Riu System. In: AIIDE, pp. 51–56. The AAAI Press (2010)Google Scholar
  10. 10.
    Recio-García, J.A., Díaz-Agudo, B., González-Calero, P.A.: Textual cbr in jcolibri: From retrieval to reuse. In: Wilson, D.C., Khemani, D. (eds.) Proceedings of the ICCBR 2007 Workshop on Textual Case-Based Reasoning: Beyond Retrieval, pp. 217–226 (August 2007)Google Scholar
  11. 11.
    Reiter, E., Dale, R.: Building Natural Language Generation Systems (2000)Google Scholar
  12. 12.
    Ristad, E.S., Yianilos, P.N.: Learning string-edit distance. IEEE Trans. Pattern Anal. Mach. Intell. 20, 522–532 (1998)CrossRefGoogle Scholar
  13. 13.
    Sahlgren, M., Cöster, R.: Using bag-of-concepts to improve the performance of support vector machines in text categorization. In: Proceedings of the 20th international conference on Computational Linguistics, COLING 2004. Association for Computational Linguistics, Stroudsburg (2004)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Josep Valls
    • 1
  • Santiago Ontañón
    • 1
  1. 1.Computer Science DepartmentDrexel UniversityPhiladelphiaUSA

Personalised recommendations