Log In Sign Up

Multi-View Document Representation Learning for Open-Domain Dense Retrieval

by   Shunyu Zhang, et al.

Dense retrieval has achieved impressive advances in first-stage retrieval from a large-scale document collection, which is built on bi-encoder architecture to produce single vector representation of query and document. However, a document can usually answer multiple potential queries from different views. So the single vector representation of a document is hard to match with multi-view queries, and faces a semantic mismatch problem. This paper proposes a multi-view document representation learning framework, aiming to produce multi-view embeddings to represent documents and enforce them to align with different queries. First, we propose a simple yet effective method of generating multiple embeddings through viewers. Second, to prevent multi-view embeddings from collapsing to the same one, we further propose a global-local loss with annealed temperature to encourage the multiple viewers to better align with different potential queries. Experiments show our method outperforms recent works and achieves state-of-the-art results.


page 1

page 2

page 3

page 4


RepBERT: Contextualized Text Embeddings for First-Stage Retrieval

Although exact term match between queries and documents is the dominant ...

UnifieR: A Unified Retriever for Large-Scale Retrieval

Large-scale retrieval is to recall relevant documents from a huge collec...

Efficient Vector Representation for Documents through Corruption

We present an efficient document representation learning framework, Docu...

On the Value of Behavioral Representations for Dense Retrieval

We consider text retrieval within dense representational space in real-w...

Multi-View Product Image Search Using Deep ConvNets Representations

Multi-view product image queries can improve retrieval performance over ...

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

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

Multi-view Factorization AutoEncoder with Network Constraints for Multi-omic Integrative Analysis

Multi-omic data provides multiple views of the same patients. Integrativ...