A TV Content Augmentation System Exploiting Rule Based Named Entity Recognition Method

Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 363)


This paper presents a TV content augmentation system that enhances the contents of TV programs by retrieving context related data and presenting them to the viewers without the necessity of another device. The paper presents both the conceptual description of the system and a prototype implementation. The implementation utilizes program descriptions crawled from web resources in order to extract named entities such as person names, locations, organizations, etc. For this purpose, a rule based Named Entity Recognition (NER) algorithm is developed for Turkish texts. Information about the extracted entities is retrieved from Wikipedia with the help of semantic disambiguation and its summarized form is presented to the users. A set of experiments have been conducted on two different data sets in order to evaluate the performance of the rule based NER algorithm and the behavior of the TV content augmentation system.


Content augmentation Connected TV EPG (Electronic Program Guide) Named Entity Recognition (NER) Semantic disambiguation 



This work is supported by the Scientific and Technical Council of Turkey Grant TUBITAK EEEAG-112E111


  1. 1.
    Taylor, A., Harper, R.: Analysis of Routine TV Watching Hbits and Their İmplications for Electronic Program Guide Design, pp. 1–12 (2002)Google Scholar
  2. 2.
    Dimitrova, N., Zimmerman, J., Janevski, A., Agnihotri, L., Haas, N., Bolle, R.: Content augmentation aspects of personalized entertainment experience. In: Proceedings of Third workshop on Personalization in Future TV (2003)Google Scholar
  3. 3.
    Chattopadhyay, T., Pal, A., Garain, U.: Mash up of breaking news and contextual web information: a novel service for connected television. In: Proceedings of International Conference on Computer and Communication Networks, ICCCN (2010)Google Scholar
  4. 4.
    Martin R., Holtzman, H.: Newstream: A Multi-Device, Cross-Medium, and Socially Aware Approach to News Content, pp. 83–90. (2010)Google Scholar
  5. 5.
    Hemsley, R., Ducao, A., Toledano, E., Holtzman, H.: ContextController: Augmenting broadcast TV with Real-Time Contextual Information, pp. 833–836 (2013)Google Scholar
  6. 6.
    Prata, A., Chambel, T.: Going Beyond iTV: designing flexible video-based crossmedia interactive services as informal learning contexts. In: Proceedings of EuroITV’11—Ubiquitous TV Conference, pp. 65–74 (2011)Google Scholar
  7. 7.
    Dilek, K.: Named Entity Recognition Experiments on Turkish Texts, pp. 524–535 (2009)Google Scholar
  8. 8.
    Küçük, D., Yazıcı, A.: A hybrid named entity recognizer for Turkish. Expert Syst. Appl. 39(3), 2733–2742 (2012)CrossRefGoogle Scholar
  9. 9.
    Freitag, D.: Machine learning for information extraction in informal domains. Mach. Learn. 39, 169–202 (2000)CrossRefGoogle Scholar
  10. 10.
    Tatar, S., Cicekli, I.: Automatic rule learning exploiting morphological features for named entity recognition in Turkish. J. Inf. Sci. 37(2), 137–151 (2011)CrossRefMATHGoogle Scholar
  11. 11.
    Akın, A.A., Akın, M.D.: Zemberek, an open source nlp framework for Turkic languages. Structure (2007).
  12. 12.
    Baeza-Yates, R., Ribeiro-Neto, B.: Modern information retrieval, vol. 9. ACM press, New York (1999)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2016

Authors and Affiliations

  1. 1.Dept. of Computer Engineering METUAnkaraTurkey

Personalised recommendations