Skip to main content
SpringerLink
Log in

A Full-Text Learning to Rank Dataset for Medical Information Retrieval

  • Conference paper
Advances in Information Retrieval (ECIR 2016)

Part of the book series: Lecture Notes in Computer Science ((LNISA,volume 9626))

Included in the following conference series:

Abstract

We present a dataset for learning to rank in the medical domain, consisting of thousands of full-text queries that are linked to thousands of research articles. The queries are taken from health topics described in layman’s English on the non-commercial www.NutritionFacts.org website; relevance links are extracted at 3 levels from direct and indirect links of queries to research articles on PubMed. We demonstrate that ranking models trained on this dataset by far outperform standard bag-of-words retrieval models. The dataset can be downloaded from: www.cl.uni-heidelberg.de/statnlpgroup/nfcorpus/.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 84.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 109.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Notes

  1. 1.

    www.ncbi.nlm.nih.gov/pubmed.

  2. 2.

    For example, the USPTO and EPO provide specialized patent search facilities at www.uspto.gov/patents/process/search and www.epo.org/searching.html.

  3. 3.

    www.research.microsoft.com/en-us/um/beijing/projects/letor, www.research. microsoft.com/en-us/projects/mslr, www.webscope.sandbox.yahoo.com.

  4. 4.

    www.clefehealth2014.dcu.ie/task-3.

  5. 5.

    www.cl.uni-heidelberg.de/statnlpgroup/boostclir/wikiclir.

  6. 6.

    BM25 parameters were set to \(k_1= 1.2\), \(b= 0.75\).

  7. 7.

    Preprocessing included lowercasing, tokenizing, filtering punctuation and stop-words, and replacing numbers with a special token.

References

  1. Bai, B., Weston, J., Grangier, D., Collobert, R., Sadamasa, K., Qi, Y., Chapelle, O., Weinberger, K.: Learning to rank with (a lot of) word features. Inf. Retr. J. 13(3), 291–314 (2010)

    Article  Google Scholar 

  2. Collins, M., Koo, T.: Discriminative reranking for natural language parsing. Comput. Linguist. 31(1), 25–69 (2005)

    Article  MathSciNet  MATH  Google Scholar 

  3. Goel, S., Langford, J., Strehl, A.L.: Predictive indexing for fast search. In: NIPS, Vancouver, Canada (2008)

    Google Scholar 

  4. Goeuriot, L., Kelly, L., Jones, G.J.F., Müller, H., Zobel, J.: Report on the SIGIR 2014 workshop on medical information retrieval (MedIR). SIGIR Forum 48(2), 78–82 (2014)

    Article  Google Scholar 

  5. Shi, Q., Petterson, J., Dror, G., Langford, J., Smola, A.J., Strehl, A.L., Vishwanathan, V.: Hash Kernels. In: AISTATS, Irvine, CA (2009)

    Google Scholar 

  6. Smucker, M.D., Allan, J., Carterette, B.: A comparison of statistical significance tests for information retrieval evaluation. In: CIKM, Lisbon, Portugal (2007)

    Google Scholar 

  7. Sokolov, A., Jehl, L., Hieber, F., Riezler, S.: Boosting cross-language retrieval by learning bilingual phrase associations from relevance rankings. In: EMNLP, Seattle (2013)

    Google Scholar 

Download references

Acknowledgments

We are grateful to Dr. Michael Greger for permitting crawling www.NutritionFacts.org. This research was supported in part by DFG grant RI-2221/1-2 “Weakly Supervised Learning of Cross-Lingual Systems”.

Author information

Authors and Affiliations

  1. Computational Linguistics, Heidelberg University, Heidelberg, Germany

    Vera Boteva, Demian Gholipour, Artem Sokolov & Stefan Riezler

  2. IWR, Heidelberg University, Heidelberg, Germany

    Stefan Riezler

Authors
  1. Vera Boteva
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Demian Gholipour
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Artem Sokolov
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Stefan Riezler
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Artem Sokolov .

Editor information

Editors and Affiliations

  1. Department of Information Engineering, University of Padua, Padova, Italy

    Nicola Ferro

  2. Faculty of Informatics, University of Lugano (USI), Lugano, Switzerland

    Fabio Crestani

  3. Department of Computer Science, Katholieke Universiteit Leuven, Heverlee, Belgium

    Marie-Francine Moens

  4. Systèmes d’informations, Big Data et Recherche d’Information, Institut de Recherche en Informatique de Toulouse IRIT/équipe SIG, Toulouse Cedex 04, France

    Josiane Mothe

  5. Yahoo! Labs London, London, UK

    Fabrizio Silvestri

  6. Department of Information Engineering, University of Padua, Padova, Italy

    Giorgio Maria Di Nunzio

  7. TU Delft - EWI/ST/WIS, Delft, The Netherlands

    Claudia Hauff

  8. Department of Information Engineering, University of Padua, Padova, Italy

    Gianmaria Silvello

Rights and permissions

Reprints and permissions

Copyright information

© 2016 Springer International Publishing Switzerland

About this paper

Cite this paper

Boteva, V., Gholipour, D., Sokolov, A., Riezler, S. (2016). A Full-Text Learning to Rank Dataset for Medical Information Retrieval. In: Ferro, N., et al. Advances in Information Retrieval. ECIR 2016. Lecture Notes in Computer Science(), vol 9626. Springer, Cham. https://doi.org/10.1007/978-3-319-30671-1_58

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-30671-1_58

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-30670-4

  • Online ISBN: 978-3-319-30671-1

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation