Iterative TempoWordNet

  • Mohammed HasanuzzamanEmail author
  • Gaël Dias
  • Stéphane Ferrari
  • Yann Mathet
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9989)


TempoWordNet (TWn) has recently been proposed as an extension of WordNet, where each synset is augmented with its temporal connotation: past, present, future or atemporal. However, recent uses of TWn show contrastive results and motivate the construction of a more reliable resource. For that purpose, we propose an iterative strategy that temporally extends glosses based on \(\text {TWn}^{t}\) to obtain a potentially more reliable \(\text {TWn}^{t+1}\). Intrinsic and extrinsic evaluation results show improvements when compared to previous versions of TWn.


Synsets Extrinsic Evaluation Reliable Resource WordNet Underlying Idea 
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.


  1. 1.
    Dias, G., Hasanuzzaman, M., Ferrari, S., Mathet, Y.: TempoWordNet for sentence time tagging. In: Companion Publication of the 23rd International Conference on World Wide Web Companion (WWW), pp. 833–838 (2014)Google Scholar
  2. 2.
    Hasanuzzaman, M., Dias, G., Ferrari, S.: Hultech at the NTCIR-11 temporalia task: ensemble learning for temporal query intent classification. In: NTCIR-11 Conference (NTCIR), pp. 478–482 (2014)Google Scholar
  3. 3.
    Hasanuzzaman, M., Dias, G., Ferrari, S., Mathet, Y.: Propagation strategies for building temporal ontologies. In: 14th Conference of the European Chapter of the Association for Computational Linguistics (EACL), pp. 6–11 (2014)Google Scholar
  4. 4.
    Joho, H., Jatowt, A., Blanco, R., Naka, H., Yamamoto, S.: Overview of NTCIR-11 temporal information access (temporalia) task. In: NTCIR-11 Conference (NTCIR), pp. 429–437 (2014)Google Scholar
  5. 5.
    Miller, G.A.: WordNet: a lexical database for English. Commun. ACM 38(11), 39–41 (1995)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2016

Authors and Affiliations

  • Mohammed Hasanuzzaman
    • 1
    Email author
  • Gaël Dias
    • 1
  • Stéphane Ferrari
    • 1
  • Yann Mathet
    • 1
  1. 1.Normandie University, UNICAEN, GREYC UMR 6072CaenFrance

Personalised recommendations