Neural Learning to Rank using TensorFlow Ranking
Rama Kumar Pasumarthi, Sebastian Bruch, Michael Bendersky, Xuanhui Wang · 2019
A number of open source packages harnessing the power of deep learning have emerged in recent years and are under active development, including TensorFlow, PyTorch and others. Supervised learning is one of the main use cases of deep learning packages. However, compared with the comprehensive support for classification or regression in open-source deep learning packages, there is a paucity of support for ranking problems. To address this gap, we developed TensorFlow Ranking: an open-source library for training large scale learning-to-rank models using deep learning in TensorFlow. The library is flexible and highly configurable: it provides an easy-to-use API to support different scoring mechanisms, loss functions, example weights, and evaluation metrics.