Listwise Learning to Rank Based on Approximate Rank Indicators
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.
Cite
Text
Thonet et al. "Listwise Learning to Rank Based on Approximate Rank Indicators." AAAI Conference on Artificial Intelligence, 2022. doi:10.1609/AAAI.V36I8.20826Markdown
[Thonet et al. "Listwise Learning to Rank Based on Approximate Rank Indicators." AAAI Conference on Artificial Intelligence, 2022.](https://mlanthology.org/aaai/2022/thonet2022aaai-listwise/) doi:10.1609/AAAI.V36I8.20826BibTeX
@inproceedings{thonet2022aaai-listwise,
title = {{Listwise Learning to Rank Based on Approximate Rank Indicators}},
author = {Thonet, Thibaut and Cinar, Yagmur Gizem and Gaussier, Éric and Li, Minghan and Renders, Jean-Michel},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2022},
pages = {8494-8502},
doi = {10.1609/AAAI.V36I8.20826},
url = {https://mlanthology.org/aaai/2022/thonet2022aaai-listwise/}
}