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.
@article{arxiv.2203.08372,
title = {Multi-View Document Representation Learning for Open-Domain Dense Retrieval},
author = {Shunyu Zhang and Yaobo Liang and Ming Gong and Daxin Jiang and Nan Duan},
journal= {arXiv preprint arXiv:2203.08372},
year = {2022}
}