Rethink Training Of BERT Rerankers In Multi-stage Retrieval Pipeline

Luyu Gao, Zhuyun Dai, Jamie Callan. Arxiv 2021 – 35 citations

[Paper]    
RAG Training Techniques Model Architecture BERT

Pre-trained deep language models~(LM) have advanced the state-of-the-art of text retrieval. Rerankers fine-tuned from deep LM estimates candidate relevance based on rich contextualized matching signals. Meanwhile, deep LMs can also be leveraged to improve search index, building retrievers with better recall. One would expect a straightforward combination of both in a pipeline to have additive performance gain. In this paper, we discover otherwise and that popular reranker cannot fully exploit the improved retrieval result. We, therefore, propose a Localized Contrastive Estimation (LCE) for training rerankers and demonstrate it significantly improves deep two-stage models.

Similar Work