Assessment of various GPU acceleration strategies in text categorization processing flow

• Autorzy: Korduła Ł. , Wielgosz M. , Karwatowski M. , Pietroń M. , Żurek D. , Wiatr K.
• Języki publikacji: EN

Abstrakty

EN

Automatic text categorization presents many difficulties. Modern algorithms are getting better in extracting meaningful information from human language. However, they often significantly increase complexity of computations. This increased demand for computational capabilities can be facilitated by the usage of hardware accelerators like general purpose graphic cards. In this paper we present a full processing flow for document categorization system. Gram-Schmidt process signatures calculation up to 12 fold decrease in computing time of system components.

Słowa kluczowe

EN

GPU; NLP; text categorization; OpenCL

• Wydawca: Wydawnictwo PAK
• Czasopismo: Measurement Automation Monitoring
• Rocznik: 2017
• Tom: Vol. 63, No. 6
• Strony: 203--205
• Opis fizyczny: Bibliogr. 5 poz., rys., tab., wykr., wzory

Twórcy

autor

Korduła Ł.

• AGH University of Science and Technology 30 Mickiewicza Av., 30-059 Cracow, Poland

autor

Wielgosz M.

• AGH University of Science and Technology 30 Mickiewicza Av., 30-059 Cracow, Poland

autor

Karwatowski M.

• AGH University of Science and Technology 30 Mickiewicza Av., 30-059 Cracow, Poland

autor

Pietroń M.

• AGH University of Science and Technology 30 Mickiewicza Av., 30-059 Cracow, Poland

autor

Żurek D.

• AGH University of Science and Technology 30 Mickiewicza Av., 30-059 Cracow, Poland

autor

Wiatr K.

• AGH University of Science and Technology 30 Mickiewicza Av., 30-059 Cracow, Poland

Bibliografia

• [1] Sebastiani Fabrizio: Machine learning in automated text categorization. ACM computing surveys (CSUR) 34.1 (2002): 1-47.
• [2] Keogh Eamonn, Abdullah Mueen: Curse of dimensionality. Encyclopedia of Machine Learning. Springer US, 2011. 257-258.
• [3] Datar M., Immorlica N., Indyk P., & Mirrokni V. S.: Locality-sensitive hashing scheme based on p-stable distributions. In: Proceedings of the twentieth annual symposium on Computational geometry, June 2004, pp. 253-262. ACM.
• [4] Milde Benjamin, Schneider Michael: Parallel implementation of classical Gram-Schmidt orthogonalization on CUDA graphics cards. TU Darmstadt Fachbereich Informatik Kryptographie und Computeralgebra, 2009.
• [5] Karwatowski M., Russek P., Wielgosz M., Koryciak S., Wiatr K.: Energy Efficient Calculations of Text Similarity Measure on FPGA-Accelerated Computing Platforms. In: International Conference on Parallel Processing and Applied Mathematics, Sept. 2015, pp. 31-40. Springer International Publishing.

Uwagi

EN

This research is supported by statutory founds of AGH UST, Department of Computer Science, Electronics and Telecommunication. No. 11.11.230.017.

PL

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę (zadania 2017).