Affiliation:
1. Minia University Faculty of Science
Abstract
Abstract
This short paper is about the first Explainable and Interactive Learning to Rank (LTR) Package in Information Retrieval (IR). This application is based on Combining the Simulated Annealing Strategy with (1+1) Evolutionary Strategy (SAS-Rank) which was introduced before as a learning algorithm for ranking in previous studies. In this application, ranking models of the offspring and parent chromosomes were shown during run time for each iteration. Furthermore, there are three options for changing the SAS-Rank parameters and seeing the evaluation results obtained. This application is the first application introducing interactive learning in the ranking problem domain for IR.
Publisher
Research Square Platform LLC
Reference23 articles.
1. Metzler, Donald and Bruce Croft, W. (2007) Linear feature-based models for information retrieval. Information Retrieval 10(3): 257--274 https://doi.org/10.1007/s10791-006-9019-z, http://dx.doi.org/10.1007/s10791-006-9019-z, 1573-7659
2. Ibrahim, Osman Ali Sadek and Younis, Eman MG (2022) Hybrid online--offline learning to rank using simulated annealing strategy based on dependent click model. Knowledge and Information Systems : 1--15 Springer
3. Nayyar, Anand and Garg, Surbhi and Gupta, Deepak and Khanna, Ashish Evolutionary computation: theory and algorithms. Advances in swarm intelligence for optimizing problems in computer science, Chapman and Hall/CRC, 2018, 1--26
4. Osman Ali Sadek Ibrahim and D. Landa-Silva (2018) An evolutionary strategy with machine learning for learning to rank in information retrieval. Soft Computing 22 https://doi.org/10.1007/s00500-017-2988-6, 10, 14337479
5. Ademir Aparecido Constantino and Walter Marcondes Filho and Dario Landa-Silva (2010) Iterated Heuristic Algorithms for the Classroom Assignment Problem. Proceedings of the: 2010 International Conference on the Practice and Theory of Automated Timetabling (PATAT 2010), Belfast, Northern Ireland, 152-166