Template-Based E-mail Summarization for Wireless Devices

  • Jason J. Jung
  • Geun-Sik Jo
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2869)


Mobile users have been suffering from low hardware capacity, poor interface, and high communication cost of their wireless devices. In this paper, we propose a wireless e-mail framework extracting user-relevant pieces of information from each e-mail text, instead of sending the full text e-mails themselves. Not only user-defined templates but also automatically generated templates based on semantic tagging are applied to be ruleset in order to discriminate which parts of the text should be extracted. E-mails that users are anticipating are especially suited to wireless notifying applications than any other kind of information. In experiments, we have verified that this system has shown an average removal of 74% redundant textual information and a maximum accurate filling of 93% of the template slots by collecting e-mails from DBWorld.


Information Extraction Short Message Service Wireless Device Template Generator Grammatical Inference 
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.
    Sadeh, N.: M-Commerce: Technologies, Services, and Business Models. Wiley computer publishing, Chichester (2002)Google Scholar
  2. 2.
    Freitag, D.: Using grammatical inference to improve precision in information extraction. In: ICML 1997 Workshop on Automata Induction, Grammatical Inference, and Language Acquisition (1997)Google Scholar
  3. 3.
    Freitag, D., McCallum, A.: Information extraction using HMMs and shrinkage. In: Proceedings of the AAAI 1999 Workshop on Machine Learning for Information Extraction (1999)Google Scholar
  4. 4.
    Doorenbos, R.B., Etzioni, O., Weld, D.S.: A Scalable Comparison-Shopping Agent for the World Wide Web. In: Proceedings of Autonomous Agent 1997 (1997)Google Scholar
  5. 5.
    Sumita, K., Miike, S., Chino, T.: Automatic Abstract Generation Based on Document Structure Analysis and Its Evaluation as a Document Retreival Presentation Function. Systems and Computers 26(13), 32–43 (1995)CrossRefGoogle Scholar
  6. 6.
    Wee, L.K.A., Tong, L.C., Tan, C.L.: A generic information extraction architecture for financial applications. Expert Systems with Applications 16(4), 343–356 (1999)CrossRefGoogle Scholar
  7. 7.
    Kushmerick, N., Weld, D.S., Doorenbos, R.: Wrapper Induction for Information Extraction. In: Intl. Joint Conference on Artificial Intelligence, pp. 729–737 (1997)Google Scholar
  8. 8.
    Crocker, D.H.: Standard For The Format Of ARPA Internet Text Messages (1982),
  9. 9.
    Maedche, A.: Ontology Learning for the Semantic Web. Kluwer Academic Publishers, Dordrecht (2002)zbMATHGoogle Scholar
  10. 10.
    Soderland, S., Fisher, D., Aseltine, J., Lehnert, W.: CRYSTAL: Inducing a Conceptual Dictionary. In: Proceedings of the Fourteenth International Joint Conference on Artificial Intelligence, pp. 1314–1319 (1995)Google Scholar
  11. 11.
    Ciravegna, F., Petrelli, D.: User involvement in customizing adaptive Information Extraction. In: Proceedings of the IJCAI 2001 Workshop on Adaptive Text Extraction and Mining (2001)Google Scholar
  12. 12.
    Open Mobile Alliance Ltd. (2002),
  13. 13.
    WAP 2.0 Specifications (2002),
  14. 14.
    Wireless Short Message Service (SMS) (2002),
  15. 15.
  16. 16.
    PalmOS Simulator,

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Jason J. Jung
    • 1
  • Geun-Sik Jo
    • 2
  1. 1.Intelligent E-Commerce Systems Laboratory, School of Computer EngineeringInha UniversityIncheonKorea
  2. 2.School of Computer EngineeringInha UniversityIncheonKorea

Personalised recommendations