An evolutionary strategy with machine learning for learning to rank in information retrieval

Ibrahim, Osman Ali Sadek; Landa-Silva, Dario

Abstract

© 2018, Springer-Verlag GmbH Germany, part of Springer Nature. Learning to rank (LTR) is one of the problems attracting researchers in information retrieval (IR). The LTR problem refers to ranking the retrieved documents for users in search engines, question answering and product recommendation systems. There is a number of LTR approaches based on machine learning and computational intelligence techniques. Most existing LTR methods have limitations, such as being too slow or not being very effective or requiring a huge computer memory to operate. This paper proposes a LTR method that combines a (1 + 1) -evolutionary strategy with machine learning. Three variants of the method are investigated: ES-Rank, IESR-Rank and IESVM-Rank. They differ on the chromosome initialisation mechanism for the evolutionary process. ES-Rank simply sets all genes in the initial chromosome to the same value. IESR-Rank uses linear regression, and IESVM-Rank uses support vector machine for the initialisation process. Experimental results from comparing the proposed method to fourteen other approaches from the literature show that IESR-Rank achieves the overall highest performance. Ten problem instances are used here, obtained from four datasets: MSLR-WEB10K, LETOR 3 and LETOR 4. Performance is measured at the top-10 query–document pairs retrieved, using five metrics: mean average precision (MAP), root-mean-square error (RMSE), precision (P@10), reciprocal rank (RR@10) and normalized discounted cumulative gain (NDCG@10). The contribution of this paper is proposing an effective and efficient LTR method combining a list-wise evolutionary technique with point-wise and pair-wise machine learning techniques.

Citation

Ibrahim, O. A. S., & Landa-Silva, D. (2018). An evolutionary strategy with machine learning for learning to rank in information retrieval. Soft Computing, 22(10), 3171-3185. https://doi.org/10.1007/s00500-017-2988-6

• Journal Article Type: Article
• Acceptance Date: Dec 7, 2017
• Online Publication Date: Jan 3, 2018
• Publication Date: 2018-05
• Deposit Date: Jan 5, 2018
• Publicly Available Date: Jan 4, 2019
• Journal: Soft Computing
• Print ISSN: 1432-7643
• Electronic ISSN: 1433-7479
• Publisher: Springer Verlag
• Peer Reviewed: Peer Reviewed
• Volume: 22
• Issue: 10
• Pages: 3171-3185
• DOI: https://doi.org/10.1007/s00500-017-2988-6
• Keywords: Learning to rank ; Evolution strategy ; Linear regression ; Support vector machine
• Public URL: https://nottingham-repository.worktribe.com/output/930734
• Publisher URL: https://link.springer.com/article/10.1007%2Fs00500-017-2988-6
• Contract Date: Jan 5, 2018