Awesome

HeckmanRank

This repository contains the code for the paper titled "Correcting for Selection Bias in Learning-to-rank Systems" which is going to appear in WWW'20, April 20-24, Taipei, Taiwan.

There are two modules in this repository:

• generation: responsible for generating semi-synthetic data
• evaluation: responsible for running experiments to evaluate HeckmanRank and baselines

The modules are located in corresponding folders. Each module is independent and has separate requirements to work with. For further details, please refer to the readme files in corresponding folders.

References

1. Zohreh Ovaisi, Ragib Ahsan, Yifan Zhang, Kathryn Vasilaky and Elena Zheleva on "Correcting for Selection Bias in Learning-to-rank Systems". Proceedings of the 29th international conference on World Wide Web, to appear.
2. Thorsten Joachims, Adith Swaminathan, Tobias Schnabel on "Unbiased Learning-to-Rank with Biased Feedback". The 10th ACM International Conference on Web Search and Data Mining.