DeepAI AI Chat
Log In Sign Up

Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One?

by   Xilun Chen, et al.

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. It has been argued that this is an inherent limitation of dense models. We disprove this claim by introducing the Salient Phrase Aware Retriever (SPAR), a dense retriever with the lexical matching capacity of a sparse model. In particular, we show that a dense retriever Λ can be trained to imitate a sparse one, and SPAR is built by augmenting a standard dense retriever with Λ. When evaluated on five open-domain question answering datasets and the MS MARCO passage retrieval task, SPAR sets a new state of the art for dense and sparse retrievers and can match or exceed the performance of more complicated dense-sparse hybrid systems.


page 1

page 2

page 3

page 4


Learning Dense Representations of Phrases at Scale

Open-domain question answering can be reformulated as a phrase retrieval...

Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index

Existing open-domain question answering (QA) models are not suitable for...

LED: Lexicon-Enlightened Dense Retriever for Large-Scale Retrieval

Retrieval models based on dense representations in semantic space have b...

Building upon Fast Multipole Methods to Detect and Model Organizations

Many models in natural and social sciences are comprised of sets of inte...

Bridging the Training-Inference Gap for Dense Phrase Retrieval

Building dense retrievers requires a series of standard procedures, incl...

Generation-Augmented Retrieval for Open-domain Question Answering

Conventional sparse retrieval methods such as TF-IDF and BM25 are simple...

Phrase Retrieval Learns Passage Retrieval, Too

Dense retrieval methods have shown great promise over sparse retrieval m...