Improving Query Representations for Dense Retrieval with Pseudo Relevance Feedback

08/30/2021
by   HongChien Yu, et al.
0

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.

READ FULL TEXT
research
06/21/2021

Pseudo-Relevance Feedback for Multiple Representation Dense Retrieval

Pseudo-relevance feedback mechanisms, from Rocchio to the relevance mode...
research
12/18/2022

Curriculum Sampling for Dense Retrieval with Document Expansion

The dual-encoder has become the de facto architecture for dense retrieva...
research
05/08/2021

Improving Document Representations by Generating Pseudo Query Embeddings for Dense Retrieval

Recently, the retrieval models based on dense representations have been ...
research
05/25/2022

Refining Query Representations for Dense Retrieval at Test Time

Dense retrieval uses a contrastive learning framework to learn dense rep...
research
06/28/2020

RepBERT: Contextualized Text Embeddings for First-Stage Retrieval

Although exact term match between queries and documents is the dominant ...
research
03/02/2023

Retrieval for Extremely Long Queries and Documents with RPRS: a Highly Efficient and Effective Transformer-based Re-Ranker

Retrieval with extremely long queries and documents is a well-known and ...
research
04/10/2023

LADER: Log-Augmented DEnse Retrieval for Biomedical Literature Search

Queries with similar information needs tend to have similar document cli...

Please sign up or login with your details

Forgot password? Click here to reset