Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback
Dense retrieval systems conduct first-stage retrieval using embedded representations and simple similarity metrics to match a query to documents. Its effectiveness depends on encoded embeddings to capture the semantics of queries and documents, a challenging task due to the shortness and ambiguity of search queries. This paper proposes ANCE-PRF, a new query encoder that uses pseudo relevance feedback (PRF) to improve query representations for dense retrieval. ANCE-PRF uses a BERT encoder that consumes the query and the top retrieved documents from a dense retrieval model, ANCE, and it learns to produce better query embeddings directly from relevance labels. It also keeps the document index unchanged to reduce overhead. ANCE-PRF significantly outperforms ANCE and other recent dense retrieval systems on several datasets. Analysis shows that the PRF encoder effectively captures the relevant and complementary information from PRF documents, while ignoring the noise with its learned attention mechanism.
Code (2)
Tasks
RetrievalMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Pseudo-Relevance Feedback for Multiple Representation Dense Retrieval
Pseudo-relevance feedback mechanisms, from Rocchio to the relevance models, have shown the usefulness of expanding and reweighting the users' initial queries using information occurring in an initial set of retrieved doc…
Information RetrievalPassage RankingRerankingRetrieval+1Optimizing Test-Time Query Representations for Dense Retrieval
Recent developments of dense retrieval rely on quality representations of queries and contexts from pre-trained query and context encoders. In this paper, we introduce TOUR (Test-Time Optimization of Query Representation…
Contrastive LearningInformation RetrievalOpen-Domain Question AnsweringPassage Retrieval+3Learning to Select: Query-Aware Adaptive Dimension Selection for Dense Retrieval
Dense retrieval represents queries and documents as high-dimensional embeddings, but these representations can be redundant at the query level: for a given information need, only a subset of dimensions is consistently he…
CAPSTONE: Curriculum Sampling for Dense Retrieval with Document Expansion
The dual-encoder has become the de facto architecture for dense retrieval. Typically, it computes the latent representations of the query and document independently, thus failing to fully capture the interactions between…
Passage RetrievalRetrievalDomain Adaptation for Dense Retrieval and Conversational Dense Retrieval through Self-Supervision by Meticulous Pseudo-Relevance Labeling
Recent studies have demonstrated that the ability of dense retrieval models to generalize to target domains with different distributions is limited, which contrasts with the results obtained with interaction-based models…
Conversational SearchDomain AdaptationRetrieval