Ranking Model Reference¶
DNN¶
Description¶
The deep neural network model for learning to rank.
This class implements a deep neural network (DNN) based ranking model. It’s essientially a multi-layer perceptron network.
Hyper Parameters¶
Linear¶
Description¶
A linear model for learning to rank.
This class implements a linear ranking model. It’s essientially a logistic regression model.
Hyper Parameters¶
DLCM¶
Description¶
The Deep Listwise Context Model for learning to rank.
This class implements the Deep Listwise Context Model (DLCM) for ranking.
See the following paper for more information.
Qingyao Ai, Keping Bi, Jiafeng Guo, W. Bruce Croft. 2018. Learning a Deep Listwise Context Model for Ranking Refinement. In Proceedings of SIGIR ‘18
Hyper Parameters¶
GSF¶
Description¶
The Groupwise Scoring Function (with no approaximation) for learning to rank.
This class implements The Groupwise Scoring Function (GSF) based on multi-layer perceptron networks.
See the following paper for more information.
Qingyao Ai, Xuanhui Wang, Sebastian Bruch, Nadav Golbandi, Michael Bendersky, Marc Najork. 2019. Learning Groupwise Scoring Functions Using Deep Neural Networks. In Proceedings of ICTIR ‘19
Hyper Parameters¶
SetRank¶
Description¶
The SetRank model for learning to rank.
This class implements the SetRank model for ranking.
See the following paper for more information.
Liang Pang, Jun Xu, Qingyao Ai, Yanyan Lan, Xueqi Cheng, Jirong Wen. 2020. SetRank: Learning a Permutation-Invariant Ranking Model for Information Retrieval. In Proceedings of SIGIR ‘20