Encyclopedia of Database Systems

Living Edition
| Editors: Ling Liu, M. Tamer Özsu

Probability Smoothing

  • Djoerd HiemstraEmail author
Living reference work entry

Later version available View entry history

DOI: https://doi.org/10.1007/978-1-4899-7993-3_936-2


Probability smoothing is a language modeling technique that assigns some nonzero probability to events that were unseen in the training data. This has the effect that the probability mass is divided over more events; hence the probability distribution becomes more smooth.

Key Points

Smoothing overcomes the so-called sparse data problem, that is, many events that are plausible in reality are not found in the data used to estimate probabilities. When using maximum likelihood estimates, unseen events are assigned a zero probability. In case of information retrieval, most events are unseen in the data, even if simple unigram language models are used documents are relatively short (say on average several hundreds of words), whereas the vocabulary is typically big (maybe millions of words), so the vast majority of words does not occur in the document. A small document about “information retrieval” might not mention the word “search,” but that does not mean it is not relevant to...
This is a preview of subscription content, log in to check access.

Recommended Reading

  1. 1.
    Chen SF, Goodman J An empirical study of smoothing techniques for language modeling. Technical report TR-10-98, Center for Research in Computing Technology, Harvard University, August 1998.Google Scholar
  2. 2.
    Zaragoza H, Hiemstra D, Tipping M, Robertson S Bayesian extension to the language model for ad hoc information retrieval. In: Proceedings of 26th annual international ACM SIGIR conference on research and development in information retrieval; 2003. p. 4–9.Google Scholar
  3. 3.
    Zhai C, Lafferty J. A study of smoothing methods for language models applied to information retrieval. ACM Trans Inf Syst. 2004;22(2):179–214.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media LLC 2017

Authors and Affiliations

  1. 1.University of TwenteEnschedeThe Netherlands

Section editors and affiliations

  • Giambattista Amati
    • 1
  1. 1.Fondazione Ugo BordoniRomeItaly