# Passage Ranking with Weak Supervision

arXiv: https://arxiv.org/abs/1905.05910 · HTML: https://mlsanity.com/paper/1905.05910/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 May 2019.

## Built on by (most cited first, 5 of 5)

- [Utilizing BERT for Information Retrieval: Survey, Applications, Resources, and Challenges](https://mlsanity.com/paper/2403.00784/) (2024)
- [Low-Resource Dense Retrieval for Open-Domain Question Answering: A Comprehensive Survey](https://mlsanity.com/paper/2208.03197/) (2022)
- [Contrastive Fine-tuning Improves Robustness for Neural Rankers](https://mlsanity.com/paper/2105.12932/) (2021)
- [A Neural Model for Joint Document and Snippet Ranking in Question Answering for Large Document Collections](https://mlsanity.com/paper/2106.08908/) (2021)
- [I Know Therefore I Score: Label-Free Crafting of Scoring Functions using Constraints Based on Domain Expertise](https://mlsanity.com/paper/2203.10085/) (2022)

## Abstract (arXiv)

In this paper, we propose a textitweak supervision framework for neural ranking tasks based on the data programming paradigm citepRatner2016, which enables us to leverage multiple weak supervision signals from different sources. Empirically, we consider two sources of weak supervision signals, unsupervised ranking functions and semantic feature similarities. We train a BERT-based passage-ranking model (which achieves new state-of-the-art performances on two benchmark datasets with full supervision) in our weak supervision framework. Without using ground-truth training labels, BERT-PR models outperform BM25 baseline by a large margin on all three datasets and even beat the previous state-of-the-art results with full supervision on two of the datasets.