Natural Language Generation from Ontologies

  • Van NguyenEmail author
  • Tran Cao SonEmail author
  • Enrico PontelliEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11372)


This paper addresses the problem of automatic generation of natural language descriptions for ontology-described artifacts. The original motivation for the work is the challenge of providing textual narratives of automatically generated scientific workflows (e.g., paragraphs that scientists can include in their publications). The paper presents two systems which generate descriptions of sets of atoms derived from a collection of ontologies. The first system, called nlgPhylogeny, demonstrates the feasibility of the task in the Phylotastic project, providing evolutionary biologists with narrative for automatically generated analysis workflows. nlgPhylogeny utilizes the fact that the Grammatical Framework (GF) is suitable for the natural language generation (NLG) task; the paper shows how elements of the ontologies in Phylotastic, such as web services and information artifacts, can be encoded in GF for the NLG task. The second system, called \(\mathtt{\small nlgOntology}^{A}\), is a generalization of nlgPhylogeny. It eliminates the requirement that a GF needs to be defined and proposes the use of annotated ontologies for NLG. Given a set of annotated ontologies, \(\mathtt{\small nlgOntology}^{A}\) generates a GF suitable for the creation of natural language descriptions of sets of atoms derived from these ontologies. The paper describes the algorithms used in the development of nlgPhylogeny and \(\mathtt{\small nlgOntology}^{A}\) and discusses potential applications of these systems.


Natural language generation Ontologies Web service Grammatical Framework Attempto Controlled English 



We thank the reviewers for the comments and the references, especially [12]. We would like to acknowledge the partial support of the NSF grants 1458595, 1401639, and 1345232.


  1. 1.
    Stoltzfus, A., et al.: Phylotastic! making tree-of-life knowledge accessible, reusable and convenient. BMC Bioinform. 14, 158 (2013)CrossRefGoogle Scholar
  2. 2.
    Angelov, K., Bringert, B., Ranta, A.: PGF: a portable run-time format for type-theoretical grammars. J. Logic Lang. Inf. 19, 201–228 (2010)CrossRefGoogle Scholar
  3. 3.
    Burden, H., Heldal, R.: Natural language generation from class diagrams. In: Proceedings of the 8th International Workshop on Model-Driven Engineering, Verification and Validation (MoDeVVa 2011), Wellington, New Zealand. ACM (2011)Google Scholar
  4. 4.
    Fuchs, N.E., Schwitter, R.: Attempto controlled English (ACE). CoRR cmp-lg/9603003 (1996)Google Scholar
  5. 5.
    Kamp, H., Reyle, U.: From Discourse to Logic. Springer, Dordrecht (1993). Scholar
  6. 6.
    Nguyen, T.H., Son, T.C., Pontelli, E.: Automatic web services composition for phylotastic. In: Calimeri, F., Hamlen, K., Leone, N. (eds.) PADL 2018. LNCS, vol. 10702, pp. 186–202. Springer, Cham (2018). Scholar
  7. 7.
    Prosdocimi, F., Chisham, B., Thompson, J., Pontelli, E., Stoltzfus, A.: Initial implementation of a comparative data analysis ontology. Evol. Bioinform. 5, 47–66 (2009)CrossRefGoogle Scholar
  8. 8.
    Ranta, A.: Grammatical framework. J. Funct. Program. 14(2), 145–189 (2004)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Ranta, A.: Grammatical framework: Programming with multilingual grammars. CSLI Publications, Center for the Study of Language and Information (2011)Google Scholar
  10. 10.
    Reiter, E., Dale, R.: Building Natural Language Generation Systems. Cambridge University Press, Cambridge (2000)CrossRefGoogle Scholar
  11. 11.
    Schwitter, R.: Specifying and verbalising answer set programs in controlled natural language (2018). arXiv preprint: arXiv:1804.10765
  12. 12.
    Vrandei, D.: Capturing meaning: Toward an abstract wikipedia.

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.New Mexico State UniversityLas CrucesUSA

Personalised recommendations