Skip to main content
SpringerLink
Log in

Query Answering to IQ Test Questions Using Word Embedding

  • Conference paper
  • First Online:
Multimedia and Network Information Systems

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 506))

  • 562 Accesses

Abstract

This paper presents an improvement over the results of Wang et al. on query answering to IQ test questions using word embedding. The improvement comes from using the Glove method and renormalization of results using the best results of two leading methods. This latter approach combines knowledge coming from different corpuses.

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 129.00
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 169.99
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

References

  1. Besold, T., Hernąndez-Orallo, J., Schmid, U.: Can Machine Intelligence be Measured in the Same Way as Human intelligence? KI 29(3): 291–297. Springer, Heidelberg (2015)

    Google Scholar 

  2. Bian, J., Chen, E., Dai, H., Gao, B., Liu, T.-Y., Tian, F., Zhang, R.: A probabilistic model for learning multi-prototype word embeddings. In: Proceedings of the 25th International Conference on Computational Linguistics (2014)

    Google Scholar 

  3. Bian, J., Gao, B., Liu, T.-Y.: Wordrep: a benchmark for research on learning word representations. CoRR (2014). arXiv:1407.1640

  4. Blei, D.M., Jordan, M.I., Ng, A.Y.: Latent dirichlet allocation. J. Mach. Learn. Res. 3, 993–1022 (2003)

    MATH  Google Scholar 

  5. Boguraev, B.K., Chu-Carroll, J., Fan, F., Fodor, P., Lally, A., McCord, M.C., Patwardhan, S., Prager, J.M.: Question analysis: How Watson reads a clue. IBM J. Res. Dev. 56(3/4) (2012)

    Google Scholar 

  6. Bordes, A., Chopra, S., Mikolov, T., Weston, J.: Towards AI-Complete Question Answering: A Set of Prerequisite Toy Tasks. ICLR (2016)

    Google Scholar 

  7. Buckland, L.P., Voorhees, E.M.: The Sixteenth Text REtrieval Conference Proceedings. NIST Special Publication 500-274 (2007)

    Google Scholar 

  8. Bullinaria, J., Levy, J.: Extracting semantic representations from word co-occurrence statistics: Stop-lists, stemming and SVD. Behav. Res. Methods 44, 890907 (2012)

    Article  Google Scholar 

  9. Carter, P.: The complete book of intelligence tests. John Wiley & Sons Ltd (2005)

    Google Scholar 

  10. Carter, P.: The Ultimate IQ Test Book: 1,000 Practice Test Questions to Boost Your Brain Power. Kogan Page Publishers (2007)

    Google Scholar 

  11. Chen, K., Corrado, G., Dean, J., Mikolov, T., Sutskever, I.: Distributed representations of words and phrases and their compositionality. CoRR (2013). arXiv:1310.4546

  12. Dowe, D.L., Hernąndez-Orallo, J., Martnez-Plumed, F., Schmid, U., Siebers, M.: Computer models solving intelligence test problems: progress and implications. Artificial Intelligence 230, 74–107 (2016)

    Article  MathSciNet  MATH  Google Scholar 

  13. Ferrucci, D.A.: Introduction to “This is Watson”, IBM J. Res. Dev. 56(3.4) ,11, IBM (2012)

    Google Scholar 

  14. Glove Large model. http://nlp.stanford.edu/data/glove.840B.300d.zip

  15. Glove Small model. http://nlp.stanford.edu/data/glove.42B.300d.zip

  16. Google News pretrained model. https://github.com/3Top/word2vec-api/blob/master/GoogleNews-vectors-negative300.bin.gz

  17. Grishman, R., Nguyen, T.H.: Employing word representations and regularization for domain adaptation of relation extraction. In: Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics, vol. 2, pp. 6874. Baltimore (2014)

    Google Scholar 

  18. Huang, E.H., Manning, C.D., Ng, A.Y., Socher, R.: Improving word representations via global context and multiple word prototypes. In: Proceedings of ACL, 873-882 (2012)

    Google Scholar 

  19. http://ai.stanford.edu/~ehhuang/

  20. Manning, C.D., Pennington, J., Socher R.: Glove:Global vectors for word representation. In: Proceedings of the Empirical Methods in Natural Language Processing (2014)

    Google Scholar 

  21. Moschitti, A., Plank, B.: Embedding semantic similarity in tree kernels for domain adaptation of relation extraction. In: Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics, vol. 1: Long pp., 14981507. Sofia, Bulgaria (2013)

    Google Scholar 

  22. Prade, H., Richard, G.: From Analogical Proportion to Logical Proportions. Springer, Basel (2013)

    MATH  Google Scholar 

  23. Questions and answers on-line database. http://www.indiabix.com/

  24. TAC 2008 Question Answering Track. http://www.nist.gov/tac/2008/qa/index.html

  25. Verbal questions test set. http://research.microsoft.com/en-us/um/beijing/events/DL-WSDM-2015/VerbalQuestions.zip

  26. Wang, H., Gao, B., Bian, J., Tian, F., Tie-Yan, L.: Solving verbal comprehension questions in IQ test by knowledge-powered word embedding. CoRR (2015). arXiv:1505.07909

  27. Wechsler Adult Intelligence Scale. http://wechsleradultintelligencescale.com

  28. Word2vec. https://code.google.com/p/word2vec

Download references

Acknowledgments

This work was supported by the 04/45/DSPB/0136 PUT grant.

Author information

Authors and Affiliations

  1. Institute of Control and Information Engineering, Poznan University of Technology, Poznań, Poland

    Michał Frąckowiak, Jakub Dutkiewicz, Czesław Jędrzejek, Marek Retinger & Paweł Werda

Authors
  1. Michał Frąckowiak
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jakub Dutkiewicz
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Czesław Jędrzejek
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Marek Retinger
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Paweł Werda
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Czesław Jędrzejek .

Editor information

Editors and Affiliations

  1. Department of Information Systems, Faculty of Computer Science and Management, Wrocław University of Science and Technology, Wroclaw, Poland

    Aleksander Zgrzywa

  2. Department of Information Systems, Faculty of Computer Science and Management, Wrocław University of Science and Technology, Wrocław, Poland

    Kazimierz Choroś

  3. Department of Information Systems, Faculty of Computer Science and Management, Wrocław University of Science and Technology, Wrocław, Poland

    Andrzej Siemiński

Rights and permissions

Reprints and permissions

Copyright information

© 2017 Springer International Publishing Switzerland

About this paper

Cite this paper

Frąckowiak, M., Dutkiewicz, J., Jędrzejek, C., Retinger, M., Werda, P. (2017). Query Answering to IQ Test Questions Using Word Embedding. In: Zgrzywa, A., Choroś, K., Siemiński, A. (eds) Multimedia and Network Information Systems. Advances in Intelligent Systems and Computing, vol 506. Springer, Cham. https://doi.org/10.1007/978-3-319-43982-2_25

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-43982-2_25

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-43981-5

  • Online ISBN: 978-3-319-43982-2

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation