DNR is an adversarial denoising neural reranker that extends score error minimization with three objectives to denoise retriever scores and align them with user feedback in two-stage recommender systems.
ISBN 9781450356572
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.IR 2verdicts
UNVERDICTED 2representative citing papers
Two methods using multiple unsupervised rankers for soft labels and filtering harmful examples allow learning-to-rank to beat BM25 with far fewer training examples.
citing papers explorer
-
Denoising Neural Reranker for Recommender Systems
DNR is an adversarial denoising neural reranker that extends score error minimization with three objectives to denoise retriever scores and align them with user feedback in two-stage recommender systems.
-
Learning More From Less: Towards Strengthening Weak Supervision for Ad-Hoc Retrieval
Two methods using multiple unsupervised rankers for soft labels and filtering harmful examples allow learning-to-rank to beat BM25 with far fewer training examples.