Taking Advantage of Discursive Properties for Validating Hierarchical Semantic Relations from Parallel Enumerative Structures

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9989)


This paper presents an approach for automatically validating candidate hierarchical relations extracted from parallel enumerative structures. It relies on the discursive properties of these structures and on the combination of resources of different nature, a semantic network and a distributional resource. The results show an accuracy of between 0.50 and 0.67, with a gain of 0.11 when combining the two resources.


Semantic Relation Semantic Network Distributional Resource Terra Firma Ontology Learning 
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.



Cassia Trojahn is partially supported by the French FUI SparkinData project.


  1. 1.
    Adam, C., Fabre, C., Muller, P.: Évaluer et améliorer une ressource distributionnelle : protocole d’annotation de liens sémantiques. TAL 54(1), 71–97 (2013)Google Scholar
  2. 2.
    Asher, N.: Reference to abstract objects in discourse: a philosophical semantics for natural language metaphysics. In: SLAP, vol. 50. Kluwer (1993)Google Scholar
  3. 3.
    Christophe, L.: Représentation et composition des structures visuelles et rhétoriques du textes. Approche pour la génération de textes formatés. PhD thesis (2000)Google Scholar
  4. 4.
    Fauconnier, J.P., Kamel, M.: Discovering hypernymy relations using text layout. In: Joint Conference on Lexical and Computational Semantics, Denver, pp. 249–258. ACL (2015)Google Scholar
  5. 5.
    Hovy, E., Arens, Y.: Readings in intelligent user interfaces. In: Automatic Generation of Formatted Text, pp. 256–262. Morgan Kaufmann Publishers (1998)Google Scholar
  6. 6.
    Navigli, R., Ponzetto, S.P.: BabelNet: the automatic construction, evaluation and application of a wide-coverage multilingual semantic network. Artif. Intell. 193, 217–250 (2012)MathSciNetCrossRefzbMATHGoogle Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  1. 1.Institut de Recherche en Informatique de ToulouseToulouseFrance

Personalised recommendations