RAVE (Real-time Answer Validation Engine) is a logic-based answer validator/selector designed for real-time question answering. Instead of proving a hypothesis for each answer, RAVE uses logic only for checking if a considered passage supports a correct answer at all. In this way parsing of the answers is avoided, yielding low validation/selection times. Machine learning is used for assigning local validation scores based on logical and shallow features. The subsequent aggregation of these local scores strives to be robust to duplicated information in the support passages. To achieve this, the effect of aggregation is controlled by the lexical diversity of the support passages for a given answer.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Rodrigo, A., Peñas, A., Verdejo, F.: Overview of the Answer Validation Exercise 2008. In: Peters, C., et al. (eds.) CLEF 2008. LNCS, vol. 5706, pp. 296–313. Springer, Heidelberg (2009)Google Scholar
  2. 2.
    Hartrumpf, S., Glöckner, I., Leveling, J.: Efficient question answering with question decomposition and multiple answer streams. In: Peters, C., et al. (eds.) CLEF 2008. LNCS, vol. 5706, pp. 421–428. Springer, Heidelberg (2009)Google Scholar
  3. 3.
    Glöckner, I., Pelzer, B.: Combining logic and machine learning for answering questions. In: Peters, C., et al. (eds.) CLEF 2008. LNCS, vol. 5706, pp. 401–408. Springer, Heidelberg (2009)Google Scholar
  4. 4.
    Glöckner, I.: Filtering and fusion of question-answering streams by robust textual inference. In: Proceedings of KRAQ 2007, Hyderabad, India (2007)Google Scholar
  5. 5.
    Glöckner, I.: Towards logic-based question answering under time constraints. In: Proc. 2008 IAENG Int. Conf. on Artificial Intelligence and Applications (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2009

Authors and Affiliations

  • Ingo Glöckner
    • 1
  1. 1.Intelligent Information and Communication Systems (IICS)FernUniversität in HagenHagenGermany

Personalised recommendations