Adaptive Latent Entity Expansion for Document Retrieval

TL;DR

This paper introduces an adaptive latent entity expansion method combined with neural re-ranking to improve document retrieval effectiveness, especially for complex queries, by enhancing relevance modeling and feedback precision.

Contribution

It proposes a novel Latent Entity Expansion (LEE) model and an adaptive retrieval process that together significantly improve search performance over existing methods.

Findings

Neural re-ranking before PRF improves effectiveness by 5-8%.

Including words and entities in expansion yields 2-8% NDCG gains.

The combined approach outperforms baselines on TREC datasets.

Abstract

Despite considerable progress in neural relevance ranking techniques, search engines still struggle to process complex queries effectively - both in terms of precision and recall. Sparse and dense Pseudo-Relevance Feedback (PRF) approaches have the potential to overcome limitations in recall, but are only effective with high precision in the top ranks. In this work, we tackle the problem of search over complex queries using three complementary techniques. First, we demonstrate that applying a strong neural re-ranker before sparse or dense PRF can improve the retrieval effectiveness by 5-8%. This improvement in PRF effectiveness can be attributed directly to improving the precision of the feedback set. Second, we propose an enhanced expansion model, Latent Entity Expansion (LEE), which applies fine-grained word and entity-based relevance modelling incorporating localized features. Specifically, we find that by including both words and entities for expansion achieve a further 2-8% improvement in NDCG. Our analysis also demonstrated that LEE is largely robust to its parameters across datasets and performs well on entity-centric queries. And third, we include an 'adaptive' component in the retrieval process, which iteratively refines the re-ranking pool during scoring using the expansion model and avoids re-ranking additional documents. We find that this combination of techniques achieves the best NDCG, MAP and R@1000 results on the TREC Robust 2004 and CODEC document datasets, demonstrating a significant advancement in expansion effectiveness.