Entailment Graphs for Text Analytics in the Excitement Project

  • Bernardo Magnini
  • Ido Dagan
  • Günter Neumann
  • Sebastian Pado
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8655)


In the last years, a relevant research line in Natural Language Processing has focused on detecting semantic relations among portions of text, including entailment, similarity, temporal relations, and, with a less degree, causality. The attention on such semantic relations has raised the demand to move towards more informative meaning representations, which express properties of concepts and relations among them. This demand triggered research on “statement entailment graphs”, where nodes are natural language statements (propositions), comprising of predicates with their arguments and modifiers, while edges represent entailment relations between nodes.

We report initial research that defines the properties of entailment graphs and their potential applications. Particularly, we show how entailment graphs are profitably used in the context of the European project EXCITEMENT, where they are applied for the analysis of customer interactions across multiple channels, including speech, email, chat and social media, and multiple languages (English, German, Italian).


Semantic inferences textual entailment text analytics 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Berant, J., Dagan, I., Goldberger, J.: Global Learning of Focused Entailment Graphs. In: Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics, Uppsala, Sweden, pp. 1220–1229 (2010)Google Scholar
  2. 2.
    Berant, J., Dagan, I., Goldberger, J.: Global Learning of Typed Entailment Rules. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Portland, Oregon, USA, pp. 610–619 (2011)Google Scholar
  3. 3.
    Dagan, I., Glickman, O., Magnini, B.: The Pascal recognising textual entailment challenge. In: Quiñonero-Candela, J., Dagan, I., Magnini, B., d’Alché-Buc, F. (eds.) MLCW 2005. LNCS (LNAI), vol. 3944, pp. 177–190. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  4. 4.
    Dagan, I., Dolan, B., Magnini, B., Roth, D.: Recognizing textual entailment: Rational, evaluation and approaches. Journal of Natural Language Engineering 15(04), i–xvii (2009)Google Scholar
  5. 5.
    Eads, P., McKay, B.: An Algorithm for generating subset of fixed size with a strong Minimal Change Property. Information Processing Letters 19, 131–133 (1984)CrossRefMathSciNetGoogle Scholar
  6. 6.
    Klein, D., Manning, C.D.: Accurate Unlexicalized Parsing. In: Proceedings of the 41st Meeting of the Association for Computational Linguistics, pp. 423–430 (2003)Google Scholar
  7. 7.
    Magnini, B., Zanoli, R., Dagan, I., Eichler, K., Neumann, G., Noh, T.-G., Padó, S., Stern, A., Levy, O.: The Excitement Open Platform for Textual Inferences. To appear in Proceedings of the 52nd Meeting of the Association for Computational Linguistics, Demo papers (2014)Google Scholar
  8. 8.
    Padó, S., Noh, T.-G., Stern, A., Wang, R., Zanoli, R.: Design and Realization of a Modular Architecture for Textual Entailment. Journal of Natural Language Engineering (2014)Google Scholar
  9. 9.
    Wille, R.: Restructuring lattice theory: An approach based on hierarchies of concepts. In: Ferré, S., Rudolph, S. (eds.) ICFCA 2009. LNCS, vol. 5548, pp. 314–339. Springer, Heidelberg (2009)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Bernardo Magnini
    • 1
  • Ido Dagan
    • 2
  • Günter Neumann
    • 3
  • Sebastian Pado
    • 4
  1. 1.Fondazione Bruno KesslerTrentoItaly
  2. 2.Bar Ilan UniversityIsrael
  3. 3.DFKIGermany
  4. 4.Stuttgart UniversityGermany

Personalised recommendations