Passage Ranking with Weak Supervision
arXiv:1905.05910
Abstract
In this paper, we propose a \textit{weak supervision} framework for neural ranking tasks based on the data programming paradigm \citep{Ratner2016}, 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.
6 pages, 1 figure
References in corpus (7)
- Universal Sentence Encoder
- A Deep Relevance Matching Model for Ad-hoc Retrieval
- End-to-End Neural Ad-hoc Ranking with Kernel Pooling
- Deep Learning for Answer Sentence Selection
- Data Programming: Creating Large Training Sets, Quickly
- Passage Re-ranking with BERT
- Measuring the Effects of Data Parallelism on Neural Network Training
Cited by in corpus (5)
- Embedding-based Zero-shot Retrieval through Query Generation
- Contrastive Fine-tuning Improves Robustness for Neural Rankers
- Interactive Text Ranking with Bayesian Optimisation: A Case Study on Community QA and Summarisation
- Exploiting Sentence-Level Representations for Passage Ranking
- Beyond [CLS] through Ranking by Generation