Performance Comparison of Natural Language Processing Model Based on Deep Neural Networks 


Vol. 44,  No. 7, pp. 1344-1350, Jul.  2019
10.7840/kics.2019.44.7.1344


PDF Full-Text
  Abstract

Deep neural networks with different structures in natural language processing showed different performance results even though they utilize training set with the same corpus. For this reason, before improving the structure of the model, researchers go through the process of finding a model that show good performance in general. In this paper, the accuracy of the deep neural networks is compared in various aspects with different corpus type. For our experiments, we used three neural networks and three corpus. The first model is CNN and the second model is RNN. Finally, the third model, CNN and RNN combined model. We compared the accuracy of models in terms of different data sizes, different word expressions, and different corpus, so that our work provides guidelines for selecting the appropriate neural network for natural language corpus via three comparison methods.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

T. Lee and K. Shin, "Performance Comparison of Natural Language Processing Model Based on Deep Neural Networks," The Journal of Korean Institute of Communications and Information Sciences, vol. 44, no. 7, pp. 1344-1350, 2019. DOI: 10.7840/kics.2019.44.7.1344.

[ACM Style]

Taegyeom Lee and Kyungseop Shin. 2019. Performance Comparison of Natural Language Processing Model Based on Deep Neural Networks. The Journal of Korean Institute of Communications and Information Sciences, 44, 7, (2019), 1344-1350. DOI: 10.7840/kics.2019.44.7.1344.

[KICS Style]

Taegyeom Lee and Kyungseop Shin, "Performance Comparison of Natural Language Processing Model Based on Deep Neural Networks," The Journal of Korean Institute of Communications and Information Sciences, vol. 44, no. 7, pp. 1344-1350, 7. 2019. (https://doi.org/10.7840/kics.2019.44.7.1344)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880