A Language Modeling Approach for Temporal Information Needs

Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 5993)


This work addresses information needs that have a temporal dimension conveyed by a temporal expression in the user’s query. Temporal expressions such as “in the 1990s” are frequent, easily extractable, but not leveraged by existing retrieval models. One challenge when dealing with them is their inherent uncertainty. It is often unclear which exact time interval a temporal expression refers to.

We integrate temporal expressions into a language modeling approach, thus making them first-class citizens of the retrieval model and considering their inherent uncertainty. Experiments on the New York Times Annotated Corpus using Amazon Mechanical Turk to collect queries and obtain relevance assessments demonstrate that our approach yields substantial improvements in retrieval effectiveness.


Language Modeling Temporal Information Temporal Expression Retrieval Model Relevance Assessment 
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.
    Nunes, S., et al.: Use of Temporal Expressions in Web Search. In: ECIR (2008)Google Scholar
  2. 2.
    Metzler, D., et al.: Improving Search Relevance for Implicitly Temporal Queries. In: SIGIR (2009)Google Scholar
  3. 3.
    Arikan, I., et al.: Time Will Tell: Leveraging Temporal Expressions in IR. In: WSDM (2009)Google Scholar
  4. 4.
    Baeza-Yates, R.A.: Searching the future. In: SIGIR Workshop MF/IR (2005)Google Scholar
  5. 5.
    Kalczynski, P.J., Chou, A.: Temporal document retrieval model for business news archives. Inf. Process. Manage. (2005)Google Scholar
  6. 6.
    New York Times Annotated Corpus,
  7. 7.
    Amazon Mechanical Turk,
  8. 8.
    Ponte, J.M., Croft, W.B.: A language modeling approach to information retrieval. In: SIGIR (1998)Google Scholar
  9. 9.
    Manning, C.D., et al.: Introduction to Information Retrieval. Cambridge University Press, Cambridge (2008)zbMATHGoogle Scholar
  10. 10.
    Berberich, K., et al.: A Language Modeling Approach for Temporal Information Needs. Research Report MPI-I-2010-5-001Google Scholar
  11. 11.
    Text REtrievel Conference,
  12. 12.
    Verhagen, M., et al.: Automating Temporal Annotation with TARSQI. In: ACL (2005)Google Scholar
  13. 13.
    TimeML Specification Language,
  14. 14.
  15. 15.
    Alonso, O., et al.: On the value of temporal information in information retrieval. SIGIR Forum (2007)Google Scholar
  16. 16.
    Li, X., Croft, W.B.: Time-based language models. In: CIKM (2003)Google Scholar
  17. 17.
    Dakka, W., et al.: Answering general time sensitive queries. In: CIKM (2008)Google Scholar
  18. 18.
    Kanhabua, N., Nørvåg, K.: Improving temporal language models for determining time of non-timestamped documents. In: ECDL (2008)Google Scholar
  19. 19.
    de Jong, F. et al.: Temporal language models for the disclosure of historical text. In: AHC (2005)Google Scholar
  20. 20.
    Corso, G.M.D., et al.: Ranking a stream of news. In: WWW (2005)Google Scholar
  21. 21.
    Jones, R., Diaz, F.: Temporal profiles of queries. ACM Trans. Inf. Syst. (2007)Google Scholar
  22. 22.
    Verhagen, M., Moszkowicz, J.L.: Temporal Annotation and Representation. In: Language and Linguistics Compass (2009)Google Scholar
  23. 23.
    Zhang, Q., et al.: TOB: Timely Ontologies for Business Relations. In: WebDB (2008)Google Scholar
  24. 24.
    Koen, D.B., Bender, W.: Time frames: Temporal augmentation of the news. IBM Systems Journal (2000)Google Scholar
  25. 25.
    Google’s Timeline View,
  26. 26.
    TimeSearch History,
  27. 27.
    Alonso, O., et al.: Crowdsourcing for relevance evaluation. SIGIR Forum (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  1. 1.Max-Planck Institute for InformaticsSaarbrückenGermany

Personalised recommendations