Collective Relevance Labeling for Passage Retrieval. (arXiv:2205.03273v1 [cs.IR])

Web: http://arxiv.org/abs/2205.03273

Deep learning for Information Retrieval (IR) requires a large amount of
high-quality query-document relevance labels, but such labels are inherently
sparse. Label smoothing redistributes some observed probability mass over
unobserved instances, often uniformly, uninformed of the true distribution. In
contrast, we propose knowledge distillation for informed labeling, without
incurring high computation overheads at evaluation time. Our contribution is
designing a simple but efficient teacher model which utilizes collective
knowledge, to outperform state-of-the-arts distilled from a more complex
teacher model. Specifically, …

arxiv labeling retrieval