Efficient Hyperparameter Tuning with Grid Search for Text Categorization using kNN Approach with BM25 Similarity

被引:66
作者
Ghawi, Raji [1 ]
Pfeffer, Juergen [1 ]
机构
[1] Tech Univ Munich, Munich, Germany
来源
OPEN COMPUTER SCIENCE | 2019年 / 9卷 / 01期
关键词
hyperparameter tuning; text categorization; grid search; kNN; BM25; OPTIMIZATION;
D O I
10.1515/comp-2019-0011
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
In machine learning, hyperparameter tuning is the problem of choosing a set of optimal hyperparameters for a learning algorithm. Several approaches have been widely adopted for hyperparameter tuning, which is typically a time consuming process. We propose an efficient technique to speed up the process of hyperparameter tuning with Grid Search. We applied this technique on text categorization using kNN algorithm with BM25 similarity, where three hyperparameters need to be tuned. Our experiments show that our proposed technique is at least an order of magnitude faster than conventional tuning.
引用
收藏
页码:160 / 180
页数:21
相关论文
共 53 条
  • [31] Lewis D. D., 1998, Machine Learning: ECML-98. 10th European Conference on Machine Learning. Proceedings, P4, DOI 10.1007/BFb0026666
  • [32] Lewis David D, 1994, MACHINE LEARNING P 1, P148, DOI DOI 10.1016/B978-1-55860-335-6.50026-X
  • [33] Maclaurin D, 2015, PR MACH LEARN RES, V37, P2113
  • [34] MASAND B, 1992, SIGIR 92 : PROCEEDINGS OF THE FIFTEENTH ANNUAL INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, P59
  • [35] Moniz N., 2018, MULTISOURCE SOCIAL F
  • [36] Murata M, 2005, P 5 NTCIR WORKSH M E, P324
  • [37] Feature selection, perceptron learning, and a usability case study for text categorization
    Ng, HT
    Goh, WB
    Low, KL
    [J]. PROCEEDINGS OF THE 20TH ANNUAL INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, 1997, : 67 - 73
  • [38] The probabilistic relevance framework: BM25 and beyond
    Robertson, Stephen
    Zaragoza, Hugo
    [J]. Foundations and Trends in Information Retrieval, 2009, 3 (04): : 333 - 389
  • [39] Robertson S. E., 1994, SIGIR '94. Proceedings of the Seventeenth Annual International ACM-SIGIR Conference on Research and Development in Information Retrieval, P232
  • [40] Ruiz ME, 1999, SIGIR'99: PROCEEDINGS OF 22ND INTERNATIONAL CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, P281, DOI 10.1145/312624.312700