Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?
Xilun Chen, Kushal Lakhotia, Barlas Oguz, Anchit Gupta, Patrick Lewis, Stan Peshterliev, Yashar Mehdad, Sonal Gupta
Abstract
Despite their recent popularity and well-known advantages, dense retrievers still lag behind sparse methods such as BM25 in their ability to reliably match salient phrases and rare entities in the query and to generalize to out-of-domain data. It has been argued that this is an inherent limitation of dense models. We rebut this claim by introducing the Salient Phrase Aware Retriever (SPAR), a dense retriever with the lexical matching capacity of a sparse model. We show that a dense Lexical Model Λ can be trained to imitate a sparse one, and SPAR is built by augmenting a standard dense retriever with Λ. Empirically, SPAR shows superior performance on a range of tasks including five question answering datasets, MS MARCO passage retrieval, as well as the EntityQuestions and BEIR benchmarks for out-of-domain evaluation, exceeding the performance of state-of-the-art dense and sparse retrievers. The code and models of SPAR are available at: https://github.com/facebookresearch/dpr-scale/tree/main/spar
BibTeX
@inproceedings{chen-etal-2022-salient,
title = "Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?",
author = "Chen, Xilun and
Lakhotia, Kushal and
Oguz, Barlas and
Gupta, Anchit and
Lewis, Patrick and
Peshterliev, Stan and
Mehdad, Yashar and
Gupta, Sonal and
Yih, Wen-tau",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.19/",
doi = "10.18653/v1/2022.findings-emnlp.19",
pages = "250--262"
}