paper-with-me

Papers

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

2021-10-13 · Xilun Chen, Kushal Lakhotia, Barlas Oğuz, Anchit Gupta, Patrick Lewis, Stan Peshterliev, Yashar Mehdad, Sonal Gupta, Wen-tau Yih

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 {\Lambda} can be trained to imitate a sparse one, and SPAR is built by augmenting a standard dense retriever with {\Lambda}. 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

📄 PDF Abstract BibTeX arXiv:2110.06918

Code (2)

facebookresearch/dpr-scale 공식 구현 pytorch
facebookresearch/dpr-scale/tree/main/spar 공식 구현 pytorch

Tasks

Open-Domain Question AnsweringPassage RetrievalQuestion AnsweringRetrieval

Similar Papers 제목 키워드 기반

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

2021-11-16 · ACL ARR November 2021 11 · Anonymous

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 argu…

Open-Domain Question AnsweringPassage RetrievalQuestion AnsweringRetrieval

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

2022-08-29 · Kai Zhang, Chongyang Tao, Tao Shen, Can Xu 외

Retrieval models based on dense representations in semantic space have become an indispensable branch for first-stage retrieval. These retrievers benefit from surging advances in representation learning towards compressi…

Representation LearningRetrieval

Representation Learning for Resource-Constrained Keyphrase Generation

2022-03-15 · Di wu, Wasi Uddin Ahmad, Sunipa Dev, Kai-Wei Chang

State-of-the-art keyphrase generation methods generally depend on large annotated datasets, limiting their performance in domains with limited annotated data. To overcome this challenge, we design a data-oriented approac…

DenoisingDomain AdaptationKeyphrase GenerationLanguage Modeling+3

Bridging the Training-Inference Gap for Dense Phrase Retrieval

2022-10-25 · Gyuwan Kim, Jinhyuk Lee, Barlas Oguz, Wenhan Xiong 외

Building dense retrievers requires a series of standard procedures, including training and validating neural models and creating indexes for efficient search. However, these procedures are often misaligned in that traini…

Open-Domain Question AnsweringPassage RetrievalQuestion AnsweringRetrieval

Phrase Retrieval Learns Passage Retrieval, Too

2021-09-16 · EMNLP 2021 11 · Jinhyuk Lee, Alexander Wettig, Danqi Chen

Dense retrieval methods have shown great promise over sparse retrieval methods in a range of NLP problems. Among them, dense phrase retrieval-the most fine-grained retrieval unit-is appealing because phrases can be direc…

Entity LinkingOpen-Domain Question AnsweringPassage RetrievalQuantization+4