Hybrid and Collaborative Passage Reranking

Abstract

In passage retrieval system, the initial passage retrieval results may be unsatisfactory, which can be refined by a reranking scheme. Existing solutions to passage reranking focus on enriching the interaction between query and each passage separately, neglecting the context among the top-ranked passages in the initial retrieval list. To tackle this problem, we propose a Hybrid and Collaborative Passage Reranking (HybRank) method, which leverages the substantial similarity measurements of upstream retrievers for passage collaboration and incorporates the lexical and semantic properties of sparse and dense retrievers for reranking. Besides, built on off-the-shelf retriever features, HybRank is a plug-in reranker capable of enhancing arbitrary passage lists including previously reranked ones. Extensive experiments demonstrate the stable improvements of performance over prevalent retrieval and reranking methods, and verify the effectiveness of the core components of HybRank.

arXiv commentAccepted to Findings of ACL 2023

References in corpus (9)

• Linformer: Self-Attention with Linear Complexity
• Axial Attention in Multidimensional Transformers
• Document Expansion by Query Prediction
• Overview of the TREC 2020 deep learning track
• Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation
• Complementing Lexical Retrieval with Semantic Residual Embedding
• Distilling Dense Representations for Ranking using Tightly-Coupled Teachers
• PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval
• Adversarial Retriever-Ranker for dense text retrieval