Enhancing Documents With Multidimensional Relevance Statements In Cross-encoder Re-ranking

Abstract

In this paper, we propose a novel approach to consider multiple dimensions of relevance beyond topicality in cross-encoder re-ranking. On the one hand, current multidimensional retrieval models often use na\"ive solutions at the re-ranking stage to aggregate multiple relevance scores into an overall one. On the other hand, cross-encoder re-rankers are effective in considering topicality but are not designed to straightforwardly account for other relevance dimensions. To overcome these issues, we envisage enhancing the candidate documents -- which are retrieved by a first-stage lexical retrieval model -- with "relevance statements" related to additional dimensions of relevance and then performing a re-ranking on them with cross-encoders. In particular, here we consider an additional relevance dimension beyond topicality, which is credibility. We test the effectiveness of our solution in the context of the Consumer Health Search task, considering publicly available datasets. Our results

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyupadhyay2023enhancing

Related papers

• CODER: An Efficient Framework For Improving Retrieval Through Contextual Document Embedding Reranking (2021)7.16
• Drowning In Documents: Consequences Of Scaling Reranker Inference (2024)0.00
• Generative Retrieval Meets Multi-graded Relevance (2024)2.26
• Enhancing The Ranking Context Of Dense Retrieval Methods Through Reciprocal Nearest Neighbors (2023)4.52
• Efficient Document Ranking With Learnable Late Interactions (2024)0.00
• Injecting The BM25 Score As Text Improves Bert-based Re-rankers (2023)10.48
• On Cross-lingual Retrieval With Multilingual Text Encoders (2021)10.35
• MICE: Minimal Interaction Cross-encoders For Efficient Re-ranking (2026)0.00