Discovering Semantic Relations Using Prepositional Phrases

  • Janardhana Punuru
  • Jianhua Chen
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 7661)


Extracting semantical relations between concepts from texts is an important research issue in text mining and ontology construction. This paper presents a machine learning-based approach to semantic relation discovery using prepositional phrases. The semantic relations are characterized by the prepositions and the semantic classes of the concepts in the prepositional phrase. WordNet and word sense disambiguation are used to extract semantic classes of concepts. Preliminary experimental results are reported here showing the promise of the proposed method.


Semantic Relation Word Sense Disambiguation Prepositional Phrase Semantic Classis Semantic Constraint 
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.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Brill, E.: A simple rule-based part-of-speech tagger. In: Third Conference on Applied Natural Language Processing, pp. 152–155 (1992)Google Scholar
  2. 2.
    Ciaramita, M., Gangemi, A., Ratsch, E., Saric, J., Rojas, I.: Unsupervised learning of semantic relations between concepts of a molecular biology ontology. In: Proc. of International Joint Conference on Artificial Intelligence (IJCAI 2005), pp. 659–664 (2005)Google Scholar
  3. 3.
    Girju, R., Badulescu, A., Moldovan, D.: Learning semantic constraints for the automatic discovery of part-whole relations. In: Human Language Technologies and North American Association of Computational Linguisitics, pp. 80–87 (2003)Google Scholar
  4. 4.
    Girju, R., Moldovan, D., Tatu, M., Antohe, D.: On the semantics of noun compounds. Computer Speech and Language 19, 479–496 (2005)CrossRefGoogle Scholar
  5. 5.
    Kavalec, M., Maedche, A., Svátek, V.: Discovery of Lexical Entries for Non-taxonomic Relations in Ontology Learning. In: Van Emde Boas, P., Pokorný, J., Bieliková, M., Štuller, J. (eds.) SOFSEM 2004. LNCS, vol. 2932, pp. 249–256. Springer, Heidelberg (2004)CrossRefGoogle Scholar
  6. 6.
    Miller, G.A.: Wordnet: An on-line lexical database. International Journal of Lexicography 3(4), 235–312 (1990)CrossRefGoogle Scholar
  7. 7.
    O’Hara, T., Wiebe, J.: Classifying functional relations in factotum via wordnet hypernym associations. In: Int. Conf. on Computational Linguistics, pp. 347–359 (2003)Google Scholar
  8. 8.
    Punuru, J., Chen, J.: Automatic Acquisition of Concepts from Domain Texts. In: Proceedings of IEEE Int. Conf. on Granular Computing, pp. 424–427 (2006)Google Scholar
  9. 9.
    Punuru, J., Chen, J.: Learning Taxonomical Relations from Domain Texts using wordNet and Word Sense Disambiguation. Proceedings of IEEE Int. Conf. on Granular Computing, August 2012 (to appear)Google Scholar
  10. 10.
    Punuru, J., Chen, J.: Learning Non-Taxonomical Semantic Relations from Domain Texts. Journal of Intelligent Information Systems 38(1), 191–207 (2012)zbMATHCrossRefGoogle Scholar
  11. 11.
    Quinlan, R.J.: C4.5: Programs for Machine Learning. Morgan Kaufmann (1993)Google Scholar
  12. 12.
    Rosario, B., Hearst, M.: Classifying the semantic in noun compounds via a domain-specific lexical hierarchy. In: EMNLP 2001, pp. 82–90 (2001)Google Scholar
  13. 13.
    Schutz, A., Buitelaar, P.: RelExt: A Tool for Relation Extraction from Text in Ontology Extension. In: Gil, Y., Motta, E., Benjamins, V.R., Musen, M.A. (eds.) ISWC 2005. LNCS, vol. 3729, pp. 593–606. Springer, Heidelberg (2005)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Janardhana Punuru
    • 1
  • Jianhua Chen
    • 1
  1. 1.Computer Science Division, School of Electrical Engineering and Computer ScienceLouisiana State UniversityBaton RougeUSA

Personalised recommendations