Skip to main content
SpringerLink
Log in

Statistical Methods of Natural Language Processing on GPU

  • Conference paper
  • First Online:
Man–Machine Interactions 4

Part of the book series: Advances in Intelligent Systems and Computing ((AISC,volume 391))

  • 977 Accesses

Abstract

The following work investigates the subject of using GPGPU technology for natural language processing. Natural language processing involves analysing very large volumes of data based on sophisticated algorithms. This process can only be performed on computers with significant computing power. Parallel computing and utilisation of the processing capacity of graphics cards can help achieve the above requirements. The work presents the problem of building n-gram models of natural language based on specific text. Two algorithms were developed: a sequential one for a typical CPU and a parallel one, which uses the capacity of a GPU. The GPU algorithm was prepared using Nvidia CUDA technology. Experiments were carried out in order to compare the effectiveness of the developed algorithms depending on the size of the analysed text and the number of words in the n-grams. The results showed that a parallel type algorithm is better for a GPU environment.

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

Similar content being viewed by others

References

  1. Ghorpade, J., Parande, J., Kulkarni, M., Bawaskar, A.: GPGPU processing in CUDA architecture. Adv. Comput.: Int. J. 3(1), 105–120 (2012)

    Google Scholar 

  2. Gupta, S., Rajasekhara, M.B.: Performance analysis of GPU compared to single-core and multi-core CPU for natural language applications. Int. J. Adv. Comput. Sci. Appl. 2(5), 50–53 (2011)

    Google Scholar 

  3. Jurafsky, D., Martin, J.H.: Speech and Language Processing. Pearson Prentice Hall, New Jersey (2008)

    Google Scholar 

  4. Nagao, M., Mori, S.: A new method of N-gram statistics for large number of n and automatic extraction of words and phrases from large text data of Japanese. In: COLING 1994. vol. 1, pp. 611–615. Kyoto, Japan (1994)

    Google Scholar 

  5. NVidia: CUDA C Programming Guide ver. 5.0 (2012)

    Google Scholar 

  6. NVidia: CUFFT Library User Guide ver. 5.0 (2012)

    Google Scholar 

  7. Shiwon, C., Dong-Wook, L.: High-performance Korean morphological analyzer using the mapreduce framework on the GPU. J. Electr. Eng. Technol. 6(4), 573–579 (2011)

    Article  Google Scholar 

  8. Xiwu, G., Ruixuan, L., Kunmei, W., Bei, P., Weijun, X.: A GPU-based accelerator for Chinese word segmentation. In: Sheng, Q.Z., Wang, G., Jensen, C.S., Xu, G. (eds.) Web Technologies and Applications. LNCS, vol. 7235, pp. 231–242. Springer, Berlin (2012)

    Chapter  Google Scholar 

  9. Youngmin, Y., Chao-Yue, L., Slav, P., Keutzer, K.: Efficient parallel CKY parsing on GPUs. In: IWPT 2011. pp. 175–185. Dublin, Ireland (2011)

    Google Scholar 

Download references

Acknowledgments

This work was financed by Ministry of Science and Higher Education in Poland (research project no. N N516 499139).

Author information

Authors and Affiliations

  1. Department of Computer Engineering, Wroclaw University of Technology, Wroclaw, Poland

    Dariusz Banasiak

Authors
  1. Dariusz Banasiak
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Dariusz Banasiak .

Editor information

Editors and Affiliations

  1. Institute of Informatics, Silesian University of Technology, Gliwice, Poland

    Aleksandra Gruca

  2. Institute of Informatics, Silesian University of Technology, Gliwice, Poland

    Agnieszka Brachman

  3. Institute of Informatics, Silesian University of Technology, Gliwice, Poland

    Stanisław Kozielski

  4. Institute of Informatics, Silesian University of Technology, Gliwice, Poland

    Tadeusz CzachĂłrski

Rights and permissions

Reprints and permissions

Copyright information

© 2016 Springer International Publishing Switzerland

About this paper

Cite this paper

Banasiak, D. (2016). Statistical Methods of Natural Language Processing on GPU. In: Gruca, A., Brachman, A., Kozielski, S., Czachórski, T. (eds) Man–Machine Interactions 4. Advances in Intelligent Systems and Computing, vol 391. Springer, Cham. https://doi.org/10.1007/978-3-319-23437-3_51

Download citation

  • DOI: https://doi.org/10.1007/978-3-319-23437-3_51

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-319-23436-6

  • Online ISBN: 978-3-319-23437-3

  • eBook Packages: EngineeringEngineering (R0)

Publish with us

Policies and ethics

Search

Navigation