Listwise Learning to Rank Based on Approximate Rank Indicators

Thibaut Thonet, Yagmur Gizem Cinar, Éric Gaussier, Minghan Li, Jean-Michel Renders

Abstract

We study here a way to approximate information retrieval metrics through a softmax-based approximation of the rank indicator function. Indeed, this latter function is a key component in the design of information retrieval metrics, as well as in the design of the ranking and sorting functions. Obtaining a good approximation for it thus opens the door to differentiable approximations of many evaluation measures that can in turn be used in neural end-to-end approaches. We first prove theoretically that the approximations proposed are of good quality, prior to validate them experimentally on both learning to rank and text-based information retrieval tasks.
BibTeX
@inproceedings{thonet2022listwise,
  author = {Thibaut Thonet and Yagmur Gizem Cinar and Éric Gaussier and Minghan Li and Jean-Michel Renders},
  title = {{Listwise Learning to Rank Based on Approximate Rank Indicators}},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year = {2022},
  doi = {10.1609/aaai.v36i8.20826},
}

Loading related content...

Figure