@inproceedings{10.1145/3685650.3685658,
author = {Kulkarni, Hrishikesh and Goharian, Nazli and Frieder, Ophir and MacAvaney, Sean},
title = {LexBoost: Improving Lexical Document Retrieval with Nearest Neighbors},
year = {2024},
isbn = {979-8-4007-1169-5/24/08},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3685650.3685658},
doi = {10.1145/3685650.3685658},
abstract = {Sparse retrieval methods like BM25 are based on lexical overlap, focusing on the surface form of the terms that appear in the query and the document. The use of inverted indices in these methods leads to high retrieval efficiency. On the other hand, dense retrieval methods are based on learned dense vectors and, consequently, are effective but comparatively slow. Since sparse and dense methods approach problems differently and use complementary relevance signals, approximation methods were proposed to balance effectiveness and efficiency. For efficiency, approximation methods like HNSW are frequently used to approximate exhaustive dense retrieval. However, approximation techniques still exhibit considerably higher latency than sparse approaches. We propose LexBoost that first builds a network of dense neighbors (a corpus graph) using a dense retrieval approach while indexing. Then, during retrieval, we consider both a document's lexical relevance scores and its neighbors' scores to rank the documents. In LexBoost this remarkably simple application of the Cluster Hypothesis contributes to stronger ranking effectiveness while contributing little computational overhead (since the corpus graph is constructed offline). The method is robust across the number of neighbors considered, various fusion parameters for determining the scores, and different dataset construction methods. We also show that re-ranking on top of LexBoost outperforms traditional dense re-ranking and leads to results comparable with higher-latency exhaustive dense retrieval.},
booktitle = {Proceedings of the ACM Symposium on Document Engineering 2024},
numpages = {10},
keywords = {Lexical Retrieval, Dense Retrieval, Corpus Graph},
location = {San Jose, CA, USA},
series = {DocEng '24}
}